Ci-STEM Journal of
Intelligent Engineering Systems and Networks

Title: Next-Generation Adaptive AI Framework for Smart Healthcare Big Data Analytics
Author:
Naveed Farhana
Department of Computer Engineering, College of Computers and Information Technology, Taif University, Kingdom of Saudi Arabia.
email: d.nfmaqsud@tu.edu.sa, naveedfarhana123@gmail.com
Pages: 1-14
DOI: https://doi.org/10.55306/CJIESN.2025.010101
Abstract:

The explosive growth in the quantity of healthcare data are produced every day from IoT devices, EHRs, and wearable sensors, thus demanding sophisticated frameworks for real-time processing and prediction analytics. In this paper, we propose an Adaptive AI-Driven Big Data Processing Framework for smart healthcare, in which we highlight and tackle concerns in data velocity, scalability and privacy. The engine is powered by distributed computing using Apache Spark and container orchestration with Kubernetes for the scale and resiliency. For prediction, we adopt a HDNN that includes the RNN for the time-series analyses and a CNN for the medical image construction. The explainable AI (XAI) methods, such as SHapley Additive exPlanations (SHAP), are also incorporated for achieving the interpretability in clinical decision-making. Secured trust- Blockchain based patient data management immutability and fine grain access controls, multi cloud infrastructure optimization for storage and retrieval. The platform lends itself to use for key functions including real time monitoring of vitals, chronic conditions early alarm, personalized treatment recommender and respiratory therapy assist and critical care alert. We empirically verify that HATE is effective to process streaming health care data at high velocity, obtain higher prediction accuracy and ensure the data security. This methodology highlights the revolutionary capabilities of AI enhanced big data analytics in the development of intelligent healthcare systems of tomorrow.
Key Words: AI, Big Data Analytics Blockchain Technology, Explainable, IoT in Healthcare, Multi-Cloud Architecture, Personalized Treatment, Real-Time Data Processing, Smart Healthcare
Citation: Farhana. N., “Next-Generation Adaptive AI Framework for Smart Healthcare Big Data Analytics,” Ci-STEM Journal of Intelligent Engineering Systems and NetworksDigital Technologies and Expert Systems, Vol. 1(1), pp. 1-13, 2025

Title: EdgeSmart: Hybrid Evolutionary Optimization for Edge-AI in Smart Cities
Authors:
Sayamuddin Ahmed Jilani
Department of Computer Science & Engineering, Maulana Abul Kalam Azad University, West Bengal, India.
email: 1075sam@gmail.com
Soumitra Kumar Mandal
Department of Electrical Engineering, National Institute of Technical Teachers Training and Research, Kolkata, West Bengal, India.
email: skmandal@nitttrkol.ac.in
Pages: 15-25
DOI: https://doi.org/10.55306/CJIESN.2025.010102
Abstract:

Efficient AI Processors for AI Processing in Smart Cities Using Genetic Algorithm Optimized Edge Networks introduces a novel system which aims to enhance the efficiency of distributed edge computing systems for time critical smart urban services. It employs GA to dynamically allocate and schedule task at edge nodes in a distributed way in order to balance the load and achieve low-latency. The system utilizes genetic searching methods to find configurations better than the optimal and saves the energy with powerful processing of the device. This optimization helps making decisions in a fast, context-guided manner, as required for smart city applications such as traffic control, health control and energy saving. Experimental results validate the superior of Edge Smart performance with respect to traditional edge-aware management, and evident improvements in processing speed, energy efficiency and system scalability are shown. These results show the capability of the framework as a viable solution to facilitate the deployment of edge intelligence in AI-based smart city infrastructures.
Key Words: AI, Computational Load Balancing, Decentralized Edge Networks, Edge Computing, Edge Intelligence. Energy Efficiency, Genetic Algorithms, Internet of Things (IoT), Latency Reduction, Optimization Techniques, Real-time Distributed Systems, Resource Optimization, Smart AI Processing, Scalability, Smart Cities, Task Scheduling.
Citation: S. A. Jilani et al., “EdgeSmart: Hybrid Evolutionary Optimization for Edge-AI in Smart Cities,” Ci-STEM Journal of Intelligent Engineering Systems and Networks, Vol. 1(1), pp. 15-25, 2025, doi: 10.55306/CJIESN.2025.010102

Title: Dual-Layer Blockchain Architecture with Secure Homomorphic Indexing for Decentralized Medical Record Management
Author:
Balaiah Miska
Tata Teleservices Limited, Kolkata. India.
email: balaiah.miska@tatacommunications.com, balaiahmiska@gmail.com
Pages: 26-40
DOI: https://doi.org/10.55306/CJIESN.2025.010103
Abstract:

Successfully handling electronic health records (EHR) is a main challenge in contemporary healthcare, constricted by escalating cyber-attacks, constrained data exchange and patient - centred data management. Conventional centralized systems can be disrupted with data breaches, theft of information, and have single points of failure, which are not scalable for healthcare systems. In this paper, we propose the Dual-Layer Blockchain Architecture (DLBA) that combines a public blockchain (to record transparent access loggings) and private blockchain (to store sensitive metadata), which achieves both security and scalability. We propose a new secure homomorphic encryption hash mapping algorithm (HHMA) to support search and retrieval of the medical records while keeping the sensitive data hidden. Medical records are saved in the InterPlanetary File System(IPFS) so that the storage does not rely on any single key, it is distributed and the records will be unable to be tampered with and the access policy and the watching history are all immutable maintained by the blockchain the layers. The proposed framework ensures patient-controlled data sharing, efficient retrieval, and privacy preservation, making it a viable solution for interoperable and trustworthy medical record management. Experimental validation demonstrates reduced retrieval latency, enhanced query privacy, and improved scalability compared to conventional blockchain-only EHR systems.
Key Words: Decentralized Healthcare Systems, Dual-Layer Blockchain, Electronic Health Records (EHR), Homomorphic Hash Mapping Algorithm (HHMA), IPFS, Privacy-Preserving Retrieval, Public–Private Blockchain, Secure Homomorphic Indexing.
Citation: B. Miska., “Dual-Layer Blockchain Architecture with Secure Homomorphic Indexing for Decentralized Medical Record Management,” Ci-STEM Journal of Intelligent Engineering Systems and Networks, Vol. 1(1), pp. 26-40, 2025, doi: 10.55306/CJIESN.2025.010103

Title: Advancing Text Summarization with Enhanced RoBERTa and Knowledge Graph Integration
Author:
R. Suganya
Department of Computer Science and Engineering, RAAK College of Engineering and Technology, Puducherry, India
email: suganyasmvec@gmail.com
Pages: 41-49
DOI: https://doi.org/10.55306/CJIESN.2025.010104
Abstract:

Especially in the era of big data, extraction and summarization of short but meaningful phrases are confronted by more and more natural language processing tools. In this work we propose the context-aware summarization methods with the enhancements both based on pre-trained models Enhanced RoBERTa with HEAD architectures by structured domain information. It is grounded on auditory attention and augments a general purpose transformer stack with knowledge-driven features to obtain more coherent, informative and semantically faithful summaries. Training and Evaluation 4.1 Corpus and Preprocessing We have corpus and preprocessing pipeline as follows. We evaluate the proposed framework using the CNN/DailyMail dataset and compare it with a variety of baselines on standard ROUGE metrics. The experimental results are quite promising for context-depth capturing and improving the quality of the automatic summaries as compared to the baselines. Overall, this work contributes to the development of text summarization by migrating from transformer-based contextual learning to integration of structured knowledge, and provides scalable and adaptable methods for intelligent information retrieval.
Key Words: Transformer Models, Enhanced RoBERTa, Abstractive Summarization, Information Retrieval, ROUGE Evaluation, Natural Language Processing.
Citation: R. Suganya., “Advancing Text Summarization with Enhanced RoBERTa and Knowledge Graph Integration,” Ci-STEM Journal of Intelligent Engineering Systems and NetworksDigital Technologies and Expert Systems, Vol. 1(1), pp. 41-49, 2025, doi: 10.55306/CJIESN.2025.010104

Title: Diabetes Prediction Using Different Classification Algorithms on Data Mining – A Survey
Authors:
Raja Rao Chatla
Board of Practical Training Eastern Region, Kolkata, India.
email: crrao@bopter.gov.in
Soumitra Kumar Mandal
Department of Electrical Engineering, National Institute of Technical Teachers Training and Research, Kolkata, West Bengal, India.
email: skmandal@nitttrkol.ac.in
Pages: 50-60
DOI: https://doi.org/10.55306/CJIESN.2025.010105
Abstract:

Healthcare generates volume of data daily in different formats such as notes, reports, images and a numbers pool and so forth. But there is no scientific instrument in medicine to study this information. The data from this point on may be mined for information that can be utilized by media experts to predict future steps in the process. Cardiopathy is the most common cause of death for the general population. Early identification and risk perception is essential for the patients’ drugs and analysis of specialists. Data mining is a process that extracts information from the collected data and structures it for further use. In the present study, we pay attention to such medical decision learning design based on diabetes data and establish a smart therapeutic choice emotional supporting network for doctors. The primary objective of this study is to develop a intelligent diabetic disease prediction for analyzing diabetes malady by using database of diabetes patients. Health data are by its nature unpredictable and always changing, which makes it extremely hard to deal with. In order to tackle the challenges mentioned above, some studies have presented a range of ML approaches for detecting and prognosis of illness. This article compares a number of diabetes prediction models to find an approach for diagnosing the disease. The research aims to shed light on different methods of diagnosis for the disease, enabling patients to get treated more quickly. The prediction of the product, glucose level in blood is also predicted with advance technology, Variety of Machine Learning techniques e.g., Neural Network (NN), SVM classifier, Data mining Techniques etc which are used here for predicting result. The study hopes to find a faster and more efficient way of diagnosing the condition, so that patients can receive treatment earlier.
Key Words: Cardiopathy, Data Mining Techniques, Diagnosing, Healthcare, Intelligent Diabetic Disease Prediction, Machine Learning, Neural Network (NN), SVM classifier.
Citation: C. R. Rao., et al., “Diabetes Prediction Using Different Classification Algorithms on Data Mining – A Survey,” Ci-STEM Journal of Intelligent Engineering Systems and NetworksDigital Technologies and Expert Systems, Vol. 1(1), pp. 50-60, 2025, doi: 10.55306/CJIESN.2025.010105