Claims:The scope of the invention is defined by the following claims:

Claim:
1. A system/method for monitoring the COVID contact persons using deep learning, said system/method comprising the steps of:
a) The system should construct the DBSCAN (1) model by preprocessing the data and libraries configuration of MATLAB.
b) The system starts with the new point (2) and check the all the density (3) of the points with some properties.
c) If the point is core point (4), then we have to check whether the cluster (5) is formed or not.
d) If it is a border point (6), then we have to detect the noise and discard the process.
e) If all the points are visited (7) then consider that person as an infected (8) and process the cluster formation (9) step.
2. As per claim 1, the DBSCAN system is constructed to based on the data preprocessing and proper configurations from the libraries.
3. As per claim 1, the system checks the new point and also check the density of the points with some properties. Based on the point, we have to check the cluster is formed or not.
4. As mentioned in the claim 1, if it’s a border point then discard the process, otherwise we are finalized that, the person is infected then display the cluster information. , Description:Field of Invention
Loads of critical infections have emerged inside the past and the modern also a brand-new infection is springing up which precipitated a massive loss to human existence and in the destiny additionally we can see this form of rising infections with a view to preserve a very good control of this kind of pandemics a thorough take a look at of pandemics is wanted and also effective techniques have to be implemented. Humans convey a number of illnesses, including individual-to-character transmission, droplet spread, and airborne transmission, in addition to infected objects, meals, animal-to-human verbal exchange, and oblique contact.
Background of the invention
Severe acute respiratory syndrome corona virus 2 (SARS-CoV-2) is a novel severe acute respiratory syndrome corona virus. It was first isolated from three people with pneumonia connected to the cluster of acute respiratory illness cases in Wuhan. All structural features of the novel SARS-CoV-2 virus particle occur in related corona viruses in nature.
Corona viruses afflict tens of thousands and thousands of human beings worldwide. A key public fitness mission in dealing with such illnesses is figuring out infected, asymptomatic people with the intention to acquire antiviral remedy. Such remedy can gain each the handled individual (via way of means of enhancing pleasant and period of life) and the populace as a whole (via decreased transmission). We broaden a compartmental version of a chronic, treatable infectious sickness and use it to assess the price and effectiveness of various ranges of screening and make contact with tracing A system is disclosed for tracking a consignment which is in transit. The system includes incorporating into the consignment a tracking device which includes a radio frequency transmitter. The frequency of the transmitter is compatible with that of a mobile telephone network (WO2003/005277A1).
Contact tracing (CT) is a more focused method: Once an infected individual is diagnosed and isolated, contact persons are identified, who had potentially infectious interactions with that index case. In general, the prevalence within that group will be much higher than that in the overall population. It is effective to screen these persons, and, if necessary, to place them in quarantine or to isolate. In one embodiment, the subject is a healthcare worker and the system, methods, and devices are utilized to evaluate the overall health of the worker as part of the check-in process for work. If the population has good immune response is then it is good, but if not immune then we need the vaccines and which is the late process. The main problem we can find is the small false positivity can lead to large positivity. We will discuss different approaches to contact tracing through different papers and publications. Among all the papers the first paper for Contact tracing is a study by Hethcote and Yorke, at the time of spread of disease ganorrhea. They wrote the paper Gonorrhea transmission dynamics and control, citing the impact of contact tracing caused by a reduction in the effective transmissible of infection. Different models till date we can identify as both the network and epidemiology of the infectious diseases is linked together [US9460264B2].
The early models are based on the population like considering the total population, but in reality we can just see that the different individuals who are infected different contacts for them to whom they can pass infection, this we can say it can form ‘mixing network’. In this particular paper we can see different theories proposed by them. Standard epidemic theory, the use of simulated networks, emergent networks. Our perception of epidemiological processes is shaped in large part by networks. The restriction of interactions to those inside a network rather than the entire population delays and decreases the spread of infection: Thus, if we are attempting to a model population-level dynamics from individual level observations, network structure must be taken into account. Many of the variations between traditional random-mixing disease models and disease spread across networks have been illustrated by his work with idealized networks and pairwise approximations. The aim of such methods should be to gain an intuitive understanding of network-based epidemics and their consequences. Clearly, the ultimate aim is to provide a collection of reliable statistics that can be used to make decisions.
Models that are based on branching processes, the model calculate an infection tree, with nodes representing infected individuals and directed edges connecting infector and infected. We would rather have a forest than a tree as recoverable individuals are removed. It is now possible to represent contact tracing directly in the path of this process, as in IBMs. If a tree member is diagnosed, the adjacent nodes will indeed be tested and, if infected, isolated. The frequency of being infectious at a given time after infection is measured in order to address the nonlinear system. This statistical likelihood is the central application that enables for the quick determination of an infection's effective reproduction number or species evenness. The removal rate can be assumed using heuristic arguments even in cases of high occurrence, and a modified average field equation has also been recommended. Several research articles look at branching process models from a various angles, keeping in mind generating operations for the degree distribution of randomly selected infectious agents.
Digital contact tracing (DCT) may be able to assist address some of the major flaws in traditional CT. The advantages of DCT include the ability to quickly identify infectious contacts as well as the ability to quickly notify contacted. DCT has the potential to significantly reduce tracing delay and boost tracing probability when compared to conventional CT. These beneficial effects, however, are accompanied with a slew of technical, social, medical, and practical issues. Contacts found on portable apps must be linked to infected contacts. Privacy and information confidentiality are important aspects of DCT. Apps must be accepted by the general public. The concept of DCT, as well as its benefits and drawbacks, must be adequately presented so that citizens grasp and embrace it. Only if a big portion of the actions in DCT can the program works.
The combined analytical and theoretical examination of CT has yielded numerous results, such as the calculation of CT's effects on the transmission of illnesses and ways to estimate the influence of the tracing delay. Nonetheless, issues of practical significance need our attention. New issues have arisen as a result of advancements in pathogen genomic sequencing and DCT, for example. Mathematical models promise quick solutions, but it will take time for these higher categories to be completely understood, and this understanding to be transferred into practice. At present there are lots of COVID cases in the country and this is one of the real time example where this type of project is helpful very much. One of the really significant benefits of this technique is that it provides a foundation for risk classification, allowing officials to focus containment on infected and even at individuals rather than the entire population-demand for the devices is expected to rise, according to industry experts. Furthermore, new manufacturers are projected to enter the market, with platform-centric software solutions for manufacturing applications being the most likely. New entrants to the business would attempt to innovate and supply through modern technologies, decreasing complexity and cutting overall total operating costs.
The goal of this invention is to enhance the touch tracing fashions can locate the pathways of the inflamed individual and the community of connection to whom he met at some stage in the infection. The application of contact tracing is investigated the use of nearest neighbor methods and absolute deterministic simulations. Emerging or re-rising infectious diseases, which include SARS, Ebola, Lassa fever, tuberculosis, and, maximum recently, COVID-19, necessitate extraordinarily powerful strategies and techniques for prevention.
Summary of the invention
The premise behind our invention is that in the event of a pandemic, such as COVID-19, which can spread through human-to-human contact, there are many other diseases that have spread in the past, and good techniques to overcome this type of crisis are required. Government officials will use numerous ways, including contact tracing, to stop the spread of deadly diseases. Many different ways the contact tracing being implemented. A huge populated country like India needs new technology to manage with the huge volumes of data, this type of data analysis would have been technologically unfeasible only a few decades ago, but current advances in machine learning may be up to the challenge.
Brief Description of Drawings
The invention will be described in detail with reference to the exemplary embodiments shown in the figures wherein:
Figure 1: Architecture diagram of the proposed methodology.
Detailed description of the invention
Contact identification: includes case research to become aware of all individuals who've had the type of touch with a showed case meaning there may be a opportunity that they've been inflamed with the virus. Contacts are diagnosed through asking approximately the case’s sports and the sports and roles of the humans round them from 2 days earlier than to fourteen days after signs onset. Contact listing: entails registering all humans taken into consideration to have had touch with a showed case, informing them in their touch popularity and explaining what movements will follow. Contacts must be advised of the significance of reporting any signs early in order that early care may be given and supplied with statistics approximately a way to lessen the danger of passing at the disease.
Contact follow-up: It can be dynamic or aloof, contingent upon the danger and assets. Aloof observing includes giving data on proposals like what to do if unwell. Dynamic checking includes mentioning contacts to report their well being status consistently, for example through message or call. Follow-up requires a relationship of trust among contact and tracer. Contact discharge: involves removing contacts from the follow-up list when one of the following criteria is met: A contact finishes his/her 14 days of follow-up period. 1. A contact becomes a case and moved to a case list. 2. Subsequent investigation leads to the person being re-classified as a non-contact. 3. Subsequent investigation leads to the linked case being reclassified as a non-case. Place the database in a location accessible from inside the python environment. Write the code for performing the following operations: Read the database and import the database into a Pandas data frame; Display a sample from the database and check the format of the data in the database; Process the data according to our requirements; Plot a figure using the matplotlib plot function and we will use this figure to display a scatterplot of our data; Create a scatterplot by using the functions in the matplotlib library and display it in the figure.
Analyze the figure to get any initial inferences. Create a machine learning model by using the DBSCAN algorithm from the sklearn library. Give proper parameters to the DBSCAN model so as to make it work correctly and efficiently based on our data. Write the code for generating clusters using our model and the input taken from the user. Now store the clusters in a data structure like a list and check for further inputs from the user. Store all the clusters as the input is given by the user. Again, if the input given by the user is already processed and a cluster is generated for it, skip this input and go directly to the previously existing cluster. Now, according to the input given by the user, display all the names present in the cluster along with the input name given by the user. Properly format the output that is given out by our model to make the output more clear and un-ambiguous and useful for the end user. Display the properly formatted output back to the user.
From the above steps, we can infer that the algorithm doesn’t require any explicit training as we use it to generate clusters from the pre-existing dataset and all it has to do is crunch those big numbers and get the output as efficiently and accurately as possible. The parameters that we give to our model, like the epsilon parameter, are very important and play a crucial role in developing our model and shaping it. The first few steps show how to read the data from the database and process I and also visualize it to get a better picture of the data that we are dealing with. This helps us in properly understanding the problem giving out an effective solution based on the inferences that we gather from the data pre-processing and visualization phase.
The next few steps correspond to the model generation and execution phase where we implement all the solutions that we have planned for the problem based on the inferences that we have gathered from the above data pre-processing and visualization phase. The algorithm is DBSCAN (Density Based spacial Clustering of Applications with Noise). This algorithm, as we can see from the title uses clustering with a density-based approach and this algorithm also can handle some noise within the data points supplied to the algorithm. We can divide our invention into two modules. They are: Data pre-processing and visualization module, Contact tracing module. DBSCAN is a density-based clustering algorithm. It can form cluster on spatial or geographical data based on the density of the data points at each location coordinates. This is different from other clustering algorithms as they don’t necessarily use density-based clustering and differ significant with the DBSCAN algorithm in other ways as well such as the functionality and the working techniques.
We can say that DBSCAN is the perfect algorithm for our particular problem because of the following factors and influencing characteristics of our dataset. Our data consists of a few columns which tell us about the identity of the person along with the location coordinates of the person. Our database contains these specific values, so as to convey all the useful information that is used in contact tracing i.e., the name (which is the identity of the person) and their location coordinates at different dates and different time stamps. All this data is highly valuable in determining the contacts of any specific person and help contain the spread of any infection. The process of identifying the subsystems that make up the system, as well as the structure for subsystem interconnection, is known as system architecture design. The architectural design's purpose is to define the software system's general structure.
4 claims & 1 figure