Description:FIELD OF THE INVENTION
The present invention relates to the field of healthcare data processing systems. More specifically, it pertains to an Internet of Things (IoT)-based architecture that integrates Fog computing and machine learning techniques, particularly Gradient Boosting algorithms, to efficiently process and analyze patient data for improved medical diagnostics and patient care.
BACKGROUND OF THE INVENTION
Breast cancer stands as one of the primary causes of worldwide mortality thus demanding early accurate diagnostic methods for successful treatment. Breast cancer prediction currently faces two major challenges: diagnosis techniques take a long time to complete and human interpretation errors occur frequently. The research focuses on breast cancer prediction through machine learning model evaluation alongside feature selection optimization for enhancing clinical diagnosis precision.
Three categories of machine learning diagnostic technologies are used in the diagnosis of breast cancer nowadays: predictive analytics, AI-powered imaging analysis in mammography, and biopsy evaluation. The FDA-approved CAD systems for detection, Google DeepMind's AI, and IBM Watson for Oncology's assistance technologies all help radiologists become more accurate and efficient.
Early breast cancer detection stands crucial for worldwide female survival rates because it remains among the most common cancers women face globally. Modern techniques of artificial intelligence (AI) together with machine learning have improved the accuracy levels of breast cancer identification in significant ways. Gradient Boosting (GB) together with improved segmentation methods provides one of the best techniques to identify breast cancer with exceptional precision.
S.No. Previous solutions Proposed solution Advantages
1 Less time and human effort Pathway for fully automated tumor categorization using machine learning models. Manual examination or semi-automated diagnostic techniques
2 Enhanced data insights and model correctness Thorough data preparation and EDA procedures. Basic or minimal pre-processing
3 Increased accuracy in diagnosis Increased precision with predictions based on machine learning Fixed algorithms and human error make it less dependable.
4 Quicker medical professionals' decision-making Offers tumor classification in real time. Postponed because of manual procedures
5 Greater generalizability across medical specialties Adaptable to various diagnostic situations and datasets Restricted to particular circumstances or datasets

The presently available solutions are shortfall in terms of:
• The use of AI diagnosis systems presently produces faulty results when distinguishing between benign and malignant tumors leading to both wrong biopsy operations and missed medical evaluations.
• Few trained Medical Learning models face difficulties when they encounter variations in patient background populations and cancer traits in actual clinical settings.
• Doctors find it challenging to decode predictions because most AI models operate as uninterpretable systems.
• The integration of AI tools presents obstacles because they need to smoothly blend with present hospital operational systems alongside electronic patient records.
• The premium costs associated with sophisticated AI-driven diagnoses make these solutions out of reach for low-resource healthcare facilities and affected populations.
SUMMARY OF THE INVENTION
This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention.
This summary is neither intended to identify key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.
The present invention introduces a comprehensive system that synergistically combines IoT end devices, Fog computing nodes, and cloud data centers to process and analyze healthcare data efficiently. This architecture is designed to minimize latency, optimize resource utilization, and enhance the accuracy of medical data analysis through the implementation of machine learning models, specifically Gradient Boosting algorithms.
In this system, IoT end devices, such as wearable health monitors and smart medical sensors, continuously collect patient health data, including vital signs and other physiological parameters. These devices are connected to gateway devices—such as smartphones or computers—that aggregate and preprocess the collected data. The gateway devices serve as intermediaries, transmitting the preprocessed data to Fog worker nodes for further analysis.
Fog worker nodes, strategically positioned at the edge of the network, are equipped with computational resources capable of executing machine learning models. Upon receiving data from the gateway devices, these nodes utilize trained Gradient Boosting models to analyze the data, identifying patterns and anomalies that may indicate medical conditions. The decentralized nature of Fog computing ensures that data processing occurs in close proximity to the data source, thereby reducing latency and enabling real-time analysis.
In scenarios where Fog worker nodes reach their maximum processing capacity or when more extensive computational resources are required, the system seamlessly offloads tasks to cloud data center nodes. A cloud controller oversees this process, managing resource allocation and ensuring efficient load balancing across the network. This hierarchical approach leverages the strengths of both Fog and cloud computing, providing a scalable solution for healthcare data processing.
The software components of the system include an information director, service director, protection supervisor, cloud controller, and service observer. The information director manages data flow, adjusting transfer speeds and merging data from multiple sources. The service director allocates resources for various applications, while the protection supervisor ensures secure communication and authentication across devices. The cloud controller supervises interactions between Fog nodes and cloud data centers, and the service observer monitors resource utilization and application performance.
By integrating IoT devices, Fog computing, and advanced machine learning models, this invention offers a robust framework for real-time healthcare data processing. It enhances the accuracy of medical diagnoses, supports timely interventions, and contributes to the overall improvement of patient care.
To further clarify advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.
Here are thorough explanations of the architecture, design, implementation, and operating methodology of the suggested invention. The architecture of this proposed invention consists of several parts, each of which is seen in Figure 1 and covered in greater detail below. For the best predictive analytics, the proposed study combines cloud computing, fog, and IoT approaches.
BRIEF DESCRIPTION OF THE DRAWINGS
The illustrated embodiments of the subject matter will be understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and methods that are consistent with the subject matter as claimed herein, wherein:
FIGURE 1: BLOCK DIAGRAM OF PROPOSED INNOVATION
FIGURE 2: BLOCK DIAGRAM ML ALGORITHM
The figures depict embodiments of the present subject matter for the purposes of illustration only. A person skilled in the art will easily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.
DETAILED DESCRIPTION OF THE INVENTION
The detailed description of various exemplary embodiments of the disclosure is described herein with reference to the accompanying drawings. It should be noted that the embodiments are described herein in such details as to clearly communicate the disclosure. However, the amount of details provided herein is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure as defined by the appended claims.
It is also to be understood that various arrangements may be devised that, although not explicitly described or shown herein, embody the principles of the present disclosure. Moreover, all statements herein reciting principles, aspects, and embodiments of the present disclosure, as well as specific examples, are intended to encompass equivalents thereof.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a",” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and/or “including,” when used herein, specify the presence of stated features, integers, steps, operations, elements and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or groups thereof.
It should also be noted that in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed concurrently or may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
In addition, the descriptions of "first", "second", “third”, and the like in the present invention are used for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Thus, features defining "first" and "second" may include at least one of the features, either explicitly or implicitly.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which example embodiments belong. It will be further understood that terms, e.g., those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Here are thorough explanations of the architecture, design, implementation, and operating methodology of the suggested invention. The architecture of this proposed invention consists of several parts, each of which is seen in Figure 1 and covered in greater detail below. For the best predictive analytics, the proposed study combines cloud computing, fog, and IoT approaches.
The proposed operation requires hardware components including the IoT end devices, gateway devices, computer, Fog worker nodes and Cloud data center nodes. IoT end devices detect scanning data after which gateway devices receive and process these data. Patient data entering through a gateway device consisting of smartphones or computers will be transmitted to master or invention nodes of the system. Similar to the Fog device operation gateway hardware performs its functions. The computer receives job requests from gateway devices either as data distribution to available invention nodes through an information director or as direct execution through a trained Machine Learning (Gradient Boosting) model to produce output. The computer transforms into a gateway device while the Fog worker nodes reach maximum capacity because it efficiently directs traffic to other Cloud-data-center nodes under supervision of a Cloud controller that ensures extra load handling. The data processing happens through a Fog worker node when a gateway device or computer requests information and then returns results using a Machine learning (Gradient Boosting) model it learned from. A deployment of worker nodes used Raspberry Pi computers throughout this research project. The Cloud-data-center node allows users to connect to Cloud resources at any time during operational needs. Software components comprising the proposed invention consist of an information director, service director, protection supervisor and the Clouds controller as well as the service observer with a Machine Learning-based model and a director. Analysis of IoT device data occurs through the functionality of the information director system.
This system possesses the capability to modify data transfer speed together with the ability to merge data from multiple sources. The information director selects the next Fog worker nodes where data will communicate. The responsibility of the service director includes budgeting enough resources for the program. The service observer of the compute server examines the resource condition of each Fog worker node and every computer that is part of the system. The catalogue of warehouse services apps helps the system evaluate the requirements of different programs. Once ready with the received information the service director proceeds to deploy necessary Cloud and Fog worker node infrastructure. The computer protection supervisor checks that gateway device authentication credentials allow users to access the system. The Fog worker node protection supervisor inspects how the Fog worker node delivers protected communication to various entities during its computer activities. A storage and resource request made in the Cloud alerts the framework to present Cloud-based instances including containers and virtual devices. Real-time execution of programs is monitored for accuracy against implementation requirements by the service observer which handles resource allocation responsibilities.
Framework Design and Implementation: The simulates IoT and Fog environments with iFog Sim to determine characteristics related to latency and congestion and energy usage and total costs. The developers can test the performance indicators of cost along with network utilization and perceived latency through iFog Sim. Fog Bus serves as a connector that resolves the transitional space between Cloud systems and IoT devices and Fog environments. Through Fog Bus developers can create IoT interfaces which do not depend on specific platforms.
Working Principle: The proposed invention is using several computational procedures. The computer is the master and Fog worker nodes are the slaves in this proposed invention. Devices such as the computer, Fog worker nodes, and gate way equipment use the same network. There are three ways to communicate: using the computer alone, using the computer and the Fog worker nodes, or using the Cloud node only. The computer completes the task and delivers the result in the first situation, whereas the Fog worker node performs this in the second. When the computer and the Fog worker nodes become over loaded due to a shortage of resources, they forward to the Clouds, functioning as a gate way device.
Gradient Boosting Algorithm using Machine Learning:
The methods used to predict breast cancer is described in this section and is depicted in Figure 2. The first step in the procedure is gathering a dataset of people who have been diagnosed with breast cancer. The collected data is then put through pre-processing steps to guarantee data quality and improve the training process' efficacy. The gradient boosting methods use the pre-processed data as input. Until the difference between the actual and predicted values approaches a small and manageable threshold, the training procedure is repeated iteratively. Machine learning is used throughout this methodology's execution. A comparison analysis is conducted to determine the best algorithm for predicting breast cancer in order to validate the technique. Recent developments in artificial intelligence (AI) and machine learning have greatly improved the detection accuracy of breast cancer. Among these, Gradient Boosting (GB) is one of the best ways to accurately detect breast cancer when paired with improved segmentation algorithms.
The detection of breast cancer relies on better segmentation technology to accurately locate tumors that appear in mammograms ultrasound and MRI scan images. The present algorithms face numerous challenges when segmenting medical images because their incapability to manage noise within insufficient contrast and overlapping tissue areas leads to numerous errors. Advanced image processing methods that combine both deep learning-based segmentation techniques with region-based segmentation and edge detection improve identification of essential features. The techniques enhance Gradient Boosting machine learning platforms which strengthen benign and malignant tumor prognosis accuracy. Improved segmentation methods lead to more precise tumor detection which prevents wrong diagnoses so physicians can diagnose cancer earlier and deliver improved treatment outcomes that raise breast cancer patient survival rates.
Gradient Boosting Machines (GBMs) exist as a methodology that functions as a wide range of machine learning algorithms for both regression and classification problems. type of machine learning algorithms widely GBMs function as regression and classification models as part of their extensive application. GBMs establish multiple prediction models that repair errors found in preceding models until perfect accuracy is achieved. The different models develop successively to correct the errors of previously built models until reaching high accuracy. previous one, until a highly accurate final model is achieved. This approach helps improve the model's performance and predictive accuracy.
ADVANTAGES OF THE INVENTION
Early breast cancer detection stands crucial for worldwide female survival rates because it remains among the most common cancers women face globally. Modern techniques of artificial intelligence (AI) together with machine learning have improved the accuracy levels of breast cancer identification in significant ways. Gradient Boosting (GB) together with improved segmentation methods provides one of the best techniques to identify breast cancer with exceptional precision.
, Claims:1. A healthcare data processing system comprising:
a plurality of IoT end devices configured to monitor and collect patient health metrics;
gateway devices that aggregate and preprocess data received from the IoT end devices;
Fog worker nodes that perform real-time data analytics and execute machine learning models on the preprocessed data;
Cloud data center nodes that provide additional computational resources and storage for advanced data processing and long-term storage;
a Cloud controller that manages task distribution between Fog worker nodes and Cloud data center nodes to optimize system performance.
2. The system as claimed in claim 1, wherein the IoT end devices include wearable sensors and medical instruments capable of wireless communication.
3. The system as claimed in claim 1, wherein the gateway devices are selected from the group consisting of smartphones, tablets, and dedicated computing units.
4. The system as claimed in claim 1, further comprising an Information Director module configured to adjust data transfer rates and merge data from multiple sources.
5. The system as claimed in claim 1, further comprising a Service Director module responsible for allocating computational and storage resources based on application requirements.
 
6. The system as claimed in claim 1, further comprising a Protection Supervisor module that authenticates gateway devices and manages user access