Capstone

Running head: HEALTH-COP COMPANY 1

HEALTH-COP COMPANY 20

Health-Cop Company

Student’s Name

Institution Affiliation

Date

Health-Cop Company

Predicting When and Where Lifestyle & Dietetic Related Health Issues Are Most Likely to Occur

Introduction

Health-cop Company is a data mining company that predicts health trends and possible illnesses that could be witnessed in the near future. The company will mainly focus on data mining and analytics to establish links between diet composition and health issues in society (Larose, 2015). The data to be used in the predictive analytics will mainly be obtained from hospital databases, nutrition and dietetics websites, health journals as well as information shared through social media platforms. Furthermore, the company will analyze purchases from food stores and groceries and also analyze the various meals ordered from various food joints. A computer algorithm programmed will be used to analyze what is being consumed in various regions and link of the food substance to a certain lifestyle-related disease would be very important (Razzak, et al., 2019). This would facilitate early detection and application of preventive measures. Health-cop Company intends to predict such issues before they can become tough to manage. These led to the main goals and objectives of the research project are;

I. To become a leader in health predictive analytics in the health sector.

II. To improve the level of preparedness for various health issues, and earn a profit from running the business.

III. To identify certain lifestyle and dietetic related illnesses that are most likely to be experienced within a certain region in the near future.

IV. To provide consolidated reports on diet composition of various people from various regions based on data obtained from websites and social media platforms.

V. To implement cloud platform to act as data heaven that will support for data storage as well as predictive data analysis.

VI. To improving its services through the adoption of innovative technologies

This paper will, therefore, seek to identify how the company intends to use the cloud platform in its operations together with Data Approach and information security to successful accomplish its goals and objectives.

Budgetary Estimation

The start-up will require planning and preparation finances to facilitate sufficient research before launching the company. Costs will also be incurred to secure strategically positioned premises for the company together with building a physically secure room will be incurred. Acquisition of digital equipment such as computers (10 desktops and 5 portable computers) and network cables as well as the installation of internet services will require sufficient funding, (Shah, et al., 2018). There will also be a cost incurred in buying a domain that will be used to access cloud resources. A server will also be procured in order to support the large network of organizations that will be linked to the company’s cloud platform. Installing the technology will also require an investment in financial resources in acquiring skilled personnel to install and maintain the cloud platform. In addition, training of human resource personnel in the company will incur some cost. Other operational expenses that are expected include training, salaries and wages for the company’s staff and marketing of the company and its services in the market.

	Things required	Estimated cost (in dollars $)
1.	Company position	2000
2.	Hardware cost	9000
3.	Software cost	3000
4.	Network cost	400
5.	Administrative cost	1000
6.	Marketing cost	100
7.	Labor and training cost	10000
	Total	25, 500

Cloud Computing

Health-cop Company is a start -up company that will offer data analytics services to various companies. The company helps heath facilities through proper service delivery to their clients through support of data analysis. The company aims at improving its services through the adoption of innovative technologies. In a review, the company aims at implementing a cloud platform to act as data heaven that will support for data storage as well as predictive data analysis. The company intends to use the software as a service approach in the cloud computing environment (Tsai, Bai, & Huang, 2014). Fetching of data will be performed through the support of the internet of things.

Content Security Policy

Considering the fact that Health-cop Company intends to use a cloud platform in data storage and handling as well as offering support for data analytics, there will be a need to have a policy that will ensure the security of data. The expected security is enabled through the website that will be used to access data from the cloud platform. The content security policy will help in detection as well as prevention of certain types of attacks that target cloud platforms (Patil, & Frederik, 2016). A content security policy will be capable of efficiently handling forms of attacks such as cross-site scripting, browser hijacking, form jacking as well as ad injecting. The company plans to have a regularly updated inventory of the first- and third-party domains, lists of whitelisted domains and a method of alerting violations of the content security policy. The company also aims to have a regular update of the policy in order to ensure that it meets data security standards.

Target Market

The company targets to sell its information to health departments at various levels of governments. The intention of targeting these companies is that they are in a position to purchase the data storage and analytics plans the company offers as the company will provide its analysis to various hospitals for an agreed fee. Health-cop will also sell its findings to private health care institutions especially nutritionists and pharmaceutical organizations. The existing competitors in the market offer predictive analytics for chronic diseases unrelated to dietetics, (Sepah, et.al., 2015). Health-cop will majorly focus on lifestyle and dietetics related illnesses that are easily preventable thus the company will be unique in the market. The major illnesses that the company will analyze and report on are diabetics, obesity, and osteoporosis. It will also provide the predictive data analysis services to companies that are in need to perform digitized and more efficient market analysis (Liu, 2014). The idea is to enable these companies to identify market niches as well as to attain competitive advantages. The company will target these companies through specialized plans that will enable favorable conditions that are economically viable.

Market Niche

With the many chronic diseases in the country, health organizations are increasingly having the need to predict the prevalence of these diseases. Health-cop services will provide the much-needed reports to health facilities. These will help health facilities draw plans on how to curb as well as prevent diseases.

Big Data Approach

As a result of the enormous amount of data required for analysis, big data approach has become a necessity for health-oriented organizations. This approach enables the companies to perform analysis in a systematic way from data repositories. The structure of storing data in a dataset is also an important aspect. The approach offers better statistical power through the tools it provides to organizations (Chen, Mao, & Liu, 2014). The approach seeks to solve challenges about handling large amounts of data. The challenges range from data analysis, storage, capture, visualization as well as information privacy.

Use of semi-custom applications

Use of semi-custom applications will form a basis for the handling big data. This technique will employ machine learning and artificial intelligence. Use of artificial and machine learning will significantly add value to the organization by providing platforms for handling big data in an efficient manner (Li, Li, Wang, Zhu, & Li, 2019). This technique will help in shaping the data analytics mindset at the Health-cop company. Customized applications will help the company convert model-based recommendations of treatment into actual insights that can be used in treatment of diabetes.

The rationale for using semi-customized applications

According to the prevailing circumstances at Health-cop Company, a semi-customized application would suit the organization in a better way. Semi customized applications take relatively short development time. Therefore, it takes a very short time to deploy these applications. When a semi-customized application is well constructed, they offer stability by offering great reliability levels as well as more resilience (Eapen, & Peterson, 2015). Semi-custom applications are more flexible offering great service through an extended lifetime, adaptability as well as their scalability. Lastly, semi-customized applications offer better quality. Their package components have robust performance levels. Moreover, they offer high-quality standards due to their applicability in many environments.

Source of Big Data

According to statistics by the world health organization, the prevalence of diabetes disease is about 9% in the unites states of America. Considering these statistics, this number of people is large. Going further to consider the daily data required to be fetched each day in monitoring disease in each patient, the data collected each day is enormous. The cloud platform will offer daily data collection from patients through the use of artificial intelligence in collaboration of sensor-based networks (Aazam, et al, 2014). The internet of things will provide support for the collection of data through miniaturized sensors. These miniaturized sensors will then be controlled through artificial intelligence. Since the cloud platform uses the software as a service technique. Each patient in the Health-cop database will have their portals that they can access services from any environment. Machine learning techniques will help in identifying patients that require urgent help. Considering all these actions that are performed on the cloud platform, big data will be generated as a result.

Storage of Data

From the proposed architectures of data storage done before, data storage will be handled through cloud storage facilities. The company aims to implement a cloud data repository. The cloud platform will provide one to many replications. One to many replications will provide data reliability as a failure of one storage node will not affect the operations in the company. It will also help in consolidating data from all remote locations, therefore, enabling an analysis of data at a central point (Jiang, et al, 2014). Storage will depend on high-speed transmissions of data from the patient's local location to the cloud storage. This will enable continuous synchronization of data in the database and therefore enabling data in the database to be up to date. This will enhance its reliability and therefore giving a clear reflection of analytics. Storage in the database will also be supported by high-speed data acceleration. Cloud storage will enable the semi-customized data-intensive health support application to collect data from the sensor sources and pass it over to the cloud (Sookhak, 2015). Data obtained will be stored by using data segmentation methods. Several segments that will range according to the type of diabetes disease on is suffering from will be enhanced. This will enable easier querying and analyzing data from the database.

Database Formats

Modern technologies have come up with formats that enable easier storage of biodata. Among the formats, is the Next Generation Sequencing. Health Cop Company intends to use this database format due to its suitability to storing biodata (Banerjee, & Sheth, 2017). Additionally, the database format is of an advantage as it will help in providing useful data mining techniques as well as machine learning techniques that will help in inputting data into specific data types and formats. The main agenda towards choosing this format is to enable Health-cop company store and analyze the data more efficiently

Network and Workflow Description

Data mining is a complex process that involves several activities undertaken sequentially for the entire process to be successful. As such, there are specific protocols that must be followed in data mining. The analysis is intended to provide new forms of data that can be interpreted to give meaningful patterns. To facilitate the process of data mining, there are several aspects that must be considered such as: statistics, clustering of data, rules of association, data classification, visualization and the decision tree.

Network Description

Health Cop company will set up is network system using both the windows and Linux based operating system. The company will have 10 desktop computers and 5 portable computers. The 10 desktop computers will be connected together via a metered Wi-Fi service. The desktops will be the main engine of the company. All the desktops will be configured with an algorithm that constantly searches for specific keywords from various databases. The portables computers will be connected to the internet via modems. A modem is much safer since it limits the connectivity to only the device being used. Internet connectivity via modem is facilitated through local area networks (LAN), through to the service providers, (Cui, et.al., 2016). Multiple firewalls are set up within the company networks to sort out undesired data traffic from the local network on the computer devices.

The most suitable firewall for the network would be a layer 3 open systems interconnection (OSI) model, which guarantees maximum security to the local network systems, (Greenberg, et.al., 2016). This type of model is well designed to suit communication within several computers in a standard network system. All the data mined from the different servers through configured search engine will be relayed to the devices whose IP addresses are saved in the network. Since all computers will be assigned specific IP addresses, resource sharing and data transfer will be effectively done via the network systems.

The network architecture will be designed with two firewalls configured into a two firewall demilitarized zone (DMZ). The DMZ is located on a neutral level that serves as the linkage and contact point between Health-Cop network systems and the internet. This is very crucial for maintaining maximum network security. This kind of security protocol also ensures that company networks are less vulnerable to any threat that may be launched via internet. Health-cop’s domain name servers will remain secured and thus the process of translating IP addresses will be much effective. Interpretation and translation of IP addresses by the regional DNS servers facilitates retrieval of data from the internet.

The switch devices have been incorporated in the network architecture since Health-cop networks will be configured on the Windows server system. Since the system is configured with layer 3 OSI, enterprise level uses must be used for the process of packet routing to be successfully executed, (Shatri, et al., 2017). This facilitates the transfer of data packets to different computers in the company system. Switches are much better compared to hubs in a network because they only relay data packets to a specific MAC address destination. Windows server system also requires routers to be installed and configured in the system to facilitate the application of virtual private network (VPN) devices.

Figure 1 Network Architecture

The network incorporates a backbone to host the two switches that have been designed in the network system. The backbone also facilitates effective communication between multiple devices operating within the Health-Cop network systems.

Work flow

The first stage of the data mining process will be data collection. The search algorithms will be configured to detect certain key words from the databases analyzed. The collected data will then be stored on the network and into the computer drives. Once the data is stored on the data, the data will be subjected to screening and cleansing procedures on the network systems. Afterwards, the data will be classified according to different clusters and patterns identified through the analysis (Adamuz-Hinojosa, et al., 2018).

Figure 2 Network diagram

The analytics will also involve regression predictions and outlier identification procedures. Finally, the data will be sorted and the relevant data sent to the network optimization unit while the data will be directed back to the regression and analysis chamber. The relevant data will be interpreted in the network optimization units and used to create patterns that explain the links between a certain dietary behaviors with a specific lifestyle disease.

Organizational Structure

The company will be headed by a chief executive officer who will be in charge of overseeing all operations. The chief executive officer is in charge of fostering a good relationship between the company and the target client companies. Through his influence, he makes approval of innovative technology such as the current impending cloud computing platform. A seven-member board of directors will be selected among data analytics professionals to undertake the duties of policy formulation and implementation. Health-cop will have a data mining division, analytics division, IT department, as well as a human resource and customer relations departments; each headed by a departmental manager. An independent division to deal with business modeling and statistical database creation will receive data from the analytics division. This division will create various projections that will be used to make predictions about specific illnesses.

Information Security

Information security is defined as the means by which data in computer systems are protected. The protection will ensure that the confidentiality, integrity, and availability of the data is maintained. Regardless, the proposal of the organization is that it is to provide data analytics services to various companies in the health sector. By taking advantage of emerging technologies such as cloud computing the company will not only be able to offer its services at competitive rates but will also be able to improve overall performance whilst ensuring data security (Peltier, 2016). Cloud computing, in general, refers to the delivery of computer resources from applications to data centers such as those that will be owned by the company. The basis of this strategy is to have easily available and secured data over the internet. Moreover, it has also been identified that the cloud service to be used is Software as a service (SaaS) (Peltier, 2016). It is the use of an application that is run by a distant computer on the cloud via a browser or internet-based application. By understanding this basis of operations, it will better demonstrate how information security will be attained.

Reasoning

The SaaS approach was selected for numerous reasons among them, its high flexibility and attractive nature to the clients. Additionally, by simplifying its installation and overall utilization, it eliminates security vulnerabilities. With security as its core value, the SaaS approach to cloud computing offered eliminates control over the hardware by the client (McCoy & Perlis, 2018). This approach is necessary for numerous reasons among them is the fact that having the hardware within the organization it will make it vulnerable to outside attacks, human error, and malicious employee activities all of which can result in data loss. This realization was after a study conducted by Accense, an analytical company, during the period of 2009 and 2014, the number of cyberattacks increased drastically (McCoy & Perlis, 2018). According to their figures, the numbers rose from a total of just over 3 million attacks per year to over 42 million attacks. For example, in 2017, the total number of data breaches cost companies an approximate of $3.6 million (McCoy & Perlis, 2018). With the figure expected to be significantly higher in 2019, the best approach to limiting cyberattacks and overall data breaches is by employing SaaS cloud services.

SaaS and Information Security

The strategy of using SaaS is advantageous because it allows numerous features to be included. This allows for the automated implementation of security measures while data is being stored or extracted from the database. Among the features present are transit protection between the client and the service. This security measure is critical as some forms of cyber-attack target data while they are in transit to the storage areas over the internet (Rittinghouse & Ransome, 2017). By using complex encryption algorithms, the data if intercepted during transmission will be useless to the hacker without the decryption key. Secondly, all user accounts will have mandatory authentication processes that will further secure the accounts of the application users. This will limit unauthorized access to the application; this strategy will be needed for any data to be transferred, added, and destroyed or manipulated (Rittinghouse & Ransome, 2017). The healthcare sector in 2017 was the most affected industry with relation to cyberattacks, by automating their security measures, future attacks can be limited.

The SaaS approach also allows for auditing or logging of activities, the objective of this security approach is to maintain accountability. By reviewing the activities of the users, malicious employees can be easily identified and the necessary disciplinary action implemented (Rittinghouse & Ransome, 2017). Finally, the SaaS platform will allow for the utilization of already available cloud computing security protocols further ensuring the safety of the data uploaded as well as the information stored. An example of the security measure in place include protection against DDoS and access regulation to prevent unexpected interceptions.

Data Valuing

When valuing the company and its data, the main area of focus was the market niche it was targeting. Technology is evolving at a rapid rate and this is especially recognizable in the healthcare industry. The majority of modern healthcare institutions have migrated from the legacy system and embraced electronic health records (Chang, Kuo, & Ramachandran, 2016). It is the digital format of medical records mandated by the HITECH (Health Information Technology for Economic and Clinical Health) Act. This act is then enforced by the ARRA (American Recovery and Reinvestment Act) of 2009 (Chang, Kuo, & Ramachandran, 2016). Nevertheless, the value collected and stored will have to undergo processes that will not only allow it to be verified but also screened to be classified in different clusters. The process allows for network optimization to be achieved thereby allowing for faster processing and storing of data collected from the client’s end. Moreover, the patterns used by the client’s in accessing as well as transmitting data are analyzed for better operations of the service (Chang, Kuo, & Ramachandran, 2016).

The whole project is estimated to take at least one year

Conclusion

A review of current marketing trends in many organizations indicates that data handling an analysis are key components of every organization. Every organization strives to ensure that they can grasp market requirements that gives them a niche in the market. For these reasons, Health-cop Company’s cloud computing project fits the market requirements of data handling and analysis. Considering the factors in play at the Health-cop company, semi-custom applications will help the company achieve its objectives in handling big data. The Next-generation sequencing database format will enable the company to store biodata more efficiently. The company’s network is designed to source for voluptuous data from various internet sources, databases and the cloud, and come up with relevant patterns that would be used to facilitate data analysis and reporting. The entire process must follow the outlined protocol for success to be achieved. Big data is the future for all industries as it offers the needed insight and understanding of operations thereby allowing for cloud computing services to progress their services. This is demonstrated by the approach that is adopted by Health Cop. The company will be sampling data with the main objective of improving the network and overall system.

References

Aazam, M., Khan, I., Alsaffar, A. A., & Huh, E. N. (2014, January). Cloud of Things: Integrating the Internet of Things and cloud computing and the issues involved. In Proceedings of 2014 11th International Bhurban Conference on Applied Sciences & Technology (IBCAST) Islamabad, Pakistan, 14th-18th January 2014 (pp. 414-419). IEEE.

Adamuz-Hinojosa, O., Ordonez-Luciana, J., Ameigeiras, P., Ramos-Munoz, J. J., Lopez, D., & Folgueira, J. (2018). Automated network service scaling in nfv: Concepts, mechanisms and scaling workflow. IEEE Communications Magazine, 56(7), 162-169.

Banerjee, T., & Sheth, A. (2017). Iot quality control for data and application needs. IEEE Intelligent Systems, 32(2), 68-73.

Chang, V., Kuo, Y. H., & Ramachandran, M. (2016). Cloud computing adoption framework: A security framework for business clouds. Future Generation Computer Systems, 57, 24-41.

Chen, M., Mao, S., & Liu, Y. (2014). Big data: A survey. Mobile networks and applications, 19(2), 171-209.

Cui, L., Yu, F. R., & Yan, Q. (2016). When big data meets software-defined networking: SDN for big data and big data for SDN. IEEE network, 30(1), 58-65.

Eapen, Z. J., & Peterson, E. D. (2015). Can mobile health applications facilitate meaningful behaviour change?: time for answers. Jama, 314(12), 1236-1237.

Goetsch, D. L., & Davis, S. B. (2014). Quality management for organizational excellence. Upper Saddle River, NJ: Pearson.

Greenberg, A., Lahiri, P., Maltz, D. A., Patel, P. K., Sengupta, S., Jain, N., & Kim, C. (2016). U.S. Patent No. 9,497,039. Washington, DC: U.S. Patent and Trademark Office.

Jiang, L., Da Xu, L., Cai, H., Jiang, Z., Bu, F., & Xu, B. (2014). An IoT-oriented data storage framework in the cloud computing platform. IEEE Transactions on Industrial Informatics, 10(2), 1443-1451.

Khoshafian, S. (2016). Service oriented enterprises. Auerbach Publications.

Larose, D. T. (2015). Data mining and predictive analytics. John Wiley & Sons.

Li, Y., Li, G., Wang, T., Zhu, Y., & Li, X. (2019). Semicustomized Design Framework of Container Accommodation for Migrant Construction Workers. Journal of Construction Engineering and Management, 145(4), 04019014.

Liu, Y. (2014). Big data and predictive business analytics. The Journal of Business Forecasting, 33(4), 40.

McCoy, T. H., & Perlis, R. H. (2018). Temporal trends and characteristics of reportable health data breaches, 2010-2017. Jama, 320(12), 1282-1284.

Patil, K., & Frederik, B. (2016). A Measurement Study of the Content Security Policy on Real-World Applications. IJ Network Security, 18(2), 383-392.

Peirson, L., Fitzpatrick-Lewis, D., Morrison, K., Ciliska, D., Kenny, M., Ali, M. U., & Raina, P. (2015). Prevention of overweight and obesity in children and youth: a systematic review and meta-analysis. CMAJ open, 3(1), E23.

Peltier, T. R. (2016). Information Security Policies, Procedures, and Standards: guidelines for effective information security management. Auerbach Publications.

Razzak, M. I., Imran, M., & Xu, G. (2019). Big data analytics for preventive medicine. Neural Computing and Applications, 1-35.

Rittinghouse, J. W., & Ransome, J. F. (2017). Cloud computing: implementation, management, and security. CRC press.

Sepah, S. C., Jiang, L., & Peters, A. L. (2015). Long-term outcomes of a Web-based diabetes prevention program: 2-year results of a single-arm longitudinal study. Journal of medical Internet research, 17(4), e92.

Shah, N. D., Sternberg, E. W., & Kent, D. M. (2018). Big data and predictive analytics: recalibrating expectations. Jama, 320(1), 27-28.

Shatri, V., Kurtaj, L., & Limani, I. (2017, May). Hardware-in-the-loop architecture with MATLAB/Simulink and QuaRC for rapid prototyping of CMAC neural network controller for ball-and-beam plant. In 2017 40th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO) (pp. 1201-1206). IEEE.

Sookhak, M. (2015). Dynamic remote data auditing for securing big data storage in cloud computing (Doctoral dissertation, University of Malaya).

Tsai, W., Bai, X., & Huang, Y. (2014). Software-as-a-service (SaaS): perspectives and challenges. Science China Information Sciences, 57(5), 1-15.