monitoring from Internet of Medical Things (IoMT) with the ecological monitoring of vector habitats by sensors.

Unique temporal granulation techniques are applied to the data to optimize processing times: Within Attribute

Granulation (WAG), Between Attribute Granulation (BAG), and Cross Dataset Granulation (CDG). A pipeline

for unsupervised classification of patient cohorts into functional infectious or non-infectious classes is based on

the similarity of clinical features and implemented using a k-Means Clustering (k-MC) procedure. The pipeline

for unsupervised classification of patient cohorts into functional class of infectious or non-infectious is based on

the similarity of clinical features and implemented through a k-Means Clustering (k-MC) procedure. Prognostic

modeling relies on Patient Severity State (PSS) vector that is evaluated by combining a Bayesian Belief Model

(BBM) for uncertainty management with an Artificial Neural Network (ANN) powered by back propagation.

The proposed dual-paradigm framework obtained an outstanding average classification Precision (93.97%) and

Chikungunya (CGN) is a fast-spreading, mosquito-borne viral disease caused by the Chikungunya virus

(CHIKV), an alphavirus belonging to the Togaviridae family. The disease is primarily transmitted to humans

when they are bitten by infected Aedes aegypti and Aedes albopictus mosquitoes, which thrive heavily within

urban and semi-urban tropical and subtropical regions containing abundant stagnant water breeding sites. Over

recent decades, globalization, irregular climate shifts, urbanization, and international travel have significantly

accelerated the geographic range of the virus. Millions of suspected and confirmed cases are reported every

year in over 60 countries spanning Asia, Africa, Europe, and the Americas.

Clinically, CGN manifests with high fever, severe polyarthralgia (intense joint pain), myalgia, headaches,

affected cohorts develop chronic, long-term joint inflammation or arthritis that persists for months or years,

without integrating localized real-time biological data with environmental dynamics such as mosquito density,

humidity, and ambient temperature anomalies. To overcome these structural limitations, there is a critical need

to design intelligent, data-driven, and context-aware public health forecasting frameworks using smart

technologies like Artificial Intelligence, Internet of Things, and Digital Twin copying structures.

Numerous studies have investigated the dynamics, transmission patterns, and control measures of the

Chikungunya virus across different geographic and climatic contexts. Chadsuthi et al. demonstrated that

microclimatic fluctuations directly dictate mosquito breeding cycles and vector distribution. Spatiotemporal

by Verma et al. and Miller et al., have established that real-time internet query mapping can provide outbreak

identification metrics with considerable lead times over slow, traditional public health clinical collection

channels.

The intersection of infectious disease informatics and digital healthcare parallel structures has attracted

significant scientific interest. Elayan et al. provided the foundational guidelines for orchestrating context-aware

Internet of Things (IoT) medical nodes, highlighting virtual replica execution to handle dynamic workflow

updates. Vats et al. improved medical trust constraints by deploying Human Digital Twin systems paired with

Explainable AI (XAI) routines to ensure medical professionals understand automated logic transitions.

Distributed data compilation has also advanced through cloud-edge frameworks: Kaur et al. designed low-

The proposed Digital Twin Framework (DTW) utilizes a layered cyber-physical configuration consisting of

Internet of Medical Things (IoMT) wearable sensor array on the patient to track primary clinical signatures

(Direct Influencing Health - DIH): core body temperature, joint pain severity indications, fatigue levels, and

muscle stiffness indices. Simultaneously, spatial coordinates are captured via smartphone GPS modules.

cryptographic containment across public network routing bounds.

matching factors across a synchronous time slice.

datasets over a defined period.

To automate patient cohort assignment without manual labeling costs, granulated host parameter matrices are

classes: Infectious and Non-Infectious. Group allocation maps multi-modal parameter metrics against moving

position coordinates of the targeted cluster center.

Prognostic evaluation is performed by a hybrid predictive setup that resolves the Patient Severity State (PSS)

vector. A Bayesian Belief Model (BBM) handles probabilistic uncertainty management across incomplete

medical records to output an accurate Health Sensitivity Measure (HSM) for each variable. These derived

probability states feed directly into a multi-layered, backpropagation-powered Artificial Neural Network

The Service layer handles the real-time alerting system. It runs an automated two-tier decision-making function

To evaluate the operational framework, a simulation domain modeling a rural region of India was built using

62,325 unique parameter entries. Relational real-time inputs were channeled using AWS cloud database

topologies over low-latency protocol gateways.