Assignment help

OriginalityReport1.pdf

Home >Information Systems homework help >Assignment help

9/14/2020 Originality Report

https://ucumberlands.blackboard.com/webapps/mdb-sa-BB5a31b16bb2c48/originalityReport/ultra?attemptId=33d3935c-b010-4d3a-a748-a6aedf709d7f&course_id=_… 1/6

%50

SafeAssign Originality Report Fall 2020 - Data Science & Big Data Analy (ITS-836-A01) - First Bi-Term • Week 2 Research Paper Big Data Analytics

%53Total Score: High riskBharat C. Submission UUID: bbf2b7fe-64e2-764a-4669-f1e0c3a3d2f5

Total Number of Reports

1 Highest Match

53 % BigDataAnalyticsandtheInternetofThings.…

Average Match

53 % Submitted on

09/06/20 07:44 PM CDT

Average Word Count

1,443 Highest: BigDataAnalyticsandtheInternet…

%53Attachment 1

Institutional database (12)

Student paper Student paper Student paper

Internet (2)

hotpaper jkoolcloud

Scholarly journals & publications (1)

ProQuest document

Top sources (3)

Excluded sources (0)

View Originality Report - Old Design

Word Count: 1,443 BigDataAnalyticsandtheInternetofThings.docx

1 12 3

7 8 15

13 9 6

4 10 5

14 2

1 Student paper 12 Student paper 3 Student paper

Running head: BIG DATA ANALYTICS 1

BIG DATA ANALYTICS 1

Big Data Analytics and the Internet of Things

Bharat Chekuri

University of the Cumberland’s

ITS-836 Data Science & Big Data Analysis

Lo'ai Tawalbeh

09/06/2020

Big Data Analytics and the Internet of Things In recent years, the use of communication and information technology has significantly impacted the evolution of com- puter-aided manufacturing. Data analytics has proven efficient in extracting crucial business elements. With the evolution in the manufacturing industry, smart

manufacturing is common, and the Internet of Things plays a crucial role in connecting the physical aspects of manufacturing to the digital space of decision-making algorithms and computing platforms. This sector comprises of diverse manufacturing controllers and equipment that are interdependent with other computing plat- forms through wireless and wired communication links. There is an influx of data traffic generated from the IoT that is either unstructured, semi-structured, and struc-

https://ucumberlands.blackboard.com/webapps/mdb-sa-BB5a31b16bb2c48/originalityReport?attemptId=33d3935c-b010-4d3a-a748-a6aedf709d7f&course_id=_130038_1&download=true&includeDeleted=true&print=true&force=true

9/14/2020 Originality Report

https://ucumberlands.blackboard.com/webapps/mdb-sa-BB5a31b16bb2c48/originalityReport/ultra?attemptId=33d3935c-b010-4d3a-a748-a6aedf709d7f&course_id=_… 2/6

tured that is generated in real-time. There are many benefits associated with the IoT, such as reducing machine downtime, improving product quality, and im-

proving factory production and operation. However, it is also associated with challenges in the data analytics life cycle. Benefits of Big Data Analytics for Manufacturing IoT The process of manufacturing involves a large amount of data that engulfs raw material supply, product distribution, logistics, and manufacturing. It is necessary to analyze big data regularly such that critical information can be extracted. The benefits of big data analytics in Manufacturing IoT includes; Improving Factory

Production and Operations Data derived from customer demands and manufacturing is important in improving machinery use, consequently improving factory oper- ations (Dey et al., 2018). For instance, some products are affected by seasonal or weather conditions like winter clothing during rainy seasons. Forecasting such condi- tions would prioritize machinery assets and the raw materials needed to meet the resultant demand. Reduces Machine Downtime Different data reflecting machinery status can be collected by deploying consistent sensors in the product line, identifying possible failures before they occur (Bi & Cochran, 2014). Automatic assembly lines also balance loads from multiple pieces of machinery through sensory data that determines excess machine loads. Improving Product Quality. Analyzing

market demand and consumer needs is important in improving the product’s design, positively impacting its demand and similar improvements (Côrte-Real et al., 2020). Analyzing manufacturing data is also important during product manufacturing, as it reduces the number of defective products by identifying the underlying problem. Consequentially, the product’s quality is improved. Enhance Supply Chain Efficiency Supply risk management in the manufacturing IoT is made possible through the proliferation of tags, RFID, and other sensors during supplier, manufacturing, and transportation (Côrte-Real et al., 2020). This factor leads to a large amount of supply chain data that, in turn, predict risks, plans logistics, and predict delivery times, among others. Analyzing inventory data also reduces holding costs and promotes safety stock levels (Dey et al., 2018). Additionally, big data analytics on the IoT aids in planning and scheduling of accurate logistic plans, ultimately lead- ing to system efficiency.

Improving Customer Experience Different companies collect information from different sources, such as social media platforms, retailers, distributors, and sales part- ners. Big data analytics, in this regard, offers solutions that are prescriptive, predictive, and descriptive, enabling companies to improve their product delivery,

quality, and design, as well as after-sales support (Dai et al., 2019). This positively impacts the customer experience. For instance, in the food industry, IoT data analyt- ics guarantee food safety. Challenges of Big Data Analytics for IoT When determining the challenges of big data analytics concerning manufacturing IoT, the following characteristics are considered; first, large social and business value, data is generated in real-time, data exists in heterogeneous forms, and data has vast volumes (Bi & Cochran, 2014). These unique features can be problematic leading to the following challenges; Data Acquisition Data acquisition involves the issues involved in data transmission and data collection. Some of these challenges include; Data Representation Difficulties IoT occurs in different dimensions, heterogeneous struc-

tures, and types. Since manufacturing data can be categorized into unstructured, semi-structured, and structured data, it poses a challenge for how exactly it should be represented under big data analytics (Ahmed et al., 2017). Efficiency in Data Transmission The question of how large amounts of data should be transmitted and stored becomes a challenge because; first, energy inefficiencies cause major constraints in wireless industrial systems like wireless sensor networks (Dey et al., 2018).

Additionally, wireless communication systems sometimes get overwhelmed with increased bandwidth consumption. Difficulties in Data Storage and Processing Data Integration Data generated from manufacturing IoT exists in different heterogeneous features and types, hence making it crucial to integrate these data types to im- plement efficient data analytics schemes (Dai et al., 2019). However, given the diverse nature of the types of manufacturing IoT data, it becomes challenging to inte- grate them. Data Redundancy There is a likelihood of data redundancy that occurs as a result of spatial and temporal redundancy from the raw data derived from IoT. This factor affects subsequent data analysis and poses a challenge as to how best to overcome redundancy. Data Compression and Data Cleaning The large amounts of data and errors recorded from the sensors make the process of data cleaning difficult. It is, therefore, crucial to implement effective measures that detect and clean errors while compressing manufacturing IoT (Dai et al., 2019). Additionally, it is not easy to design and create effective data storage mechanisms, given the nature of manufacturing IoT data. Data storage is critical in value extraction and data analysis. Persistency and Reliability of Data Storage It is critical to ensure the persistence and reliability of manufacturing IoT data storage systems. The challenge, however, comes in the form of meeting the big data analytics requirements while considering costs incurred due to the vast amount of data (Côrte-Real et al., 2020). Scalability Other than the problems incurred in storage, there comes a challenge of scalable storage systems or big data analytics. There is a likelihood of in-feasibility of the conventional databases as a result of the vast amounts of data sets of manufacturing IoT (Dai et al., 2019). Consequentially, there is a need to introduce new storage paradigms that would support tremendously large data storage systems for big

data analytics. Spatial and Temporal Correlation Since manufacturing IoT data is temporally and spatially correlated, it becomes challenging to extract and manage useful information from spatially or temporally correlated IoT data (Dai et al., 2019). Efficient Data Mining Schemes Given the increased volumes of manufacturing IoT, there is a challenge that arises given the uncertainty of erroneous manufacturing IoT data features and data errors likely to occur. Also, applying conventional multi- pass data-mining schemes would not be feasible as a result of the large data volumes. Privacy and Security. Data security and privacy become challenging to

maintain despite numerous conventional privacy-preserving data analytical schemes (Ahmed et al., 2017). These schemes may not apply to the manufacturing IoT giv- en the volume of data that needs to be analyzed. Conclusion Overall, collecting data and monitoring all activities is critical in manufacturing IoT. The data collected is important in improving daily operations and create useful and efficient impacts on productivity. The benefits often outweigh the challenges, but the latter is often as- sociated with data validity, transformation rate, solution costs, and data integration. Processing large amounts of data can be problematic, given its diverse nature and consistent heterogeneous features.

References

Ahmed, E., Yaqoob, I., Hashem, I. A. T., Khan, I., Ahmed, A. I. A., Imran, M., & Vasilakos, A. V. (2017). The role of big data analytics in the Internet of

Things. Computer Networks, 129, 459-471. Retrieved from https://doi.org/10.1016/j.comnet.2017.06.013

Bi, Z., & Cochran, D. (2014). Big data analytics with applications. Journal of Management Analytics, 1(4), 249-265. Retrieved from

https://doi.org/10.1080/23270012.2014.992985

Côrte-Real, N., Ruivo, P., & Oliveira, T. (2020). Leveraging the Internet of things and big data analytics initiatives in European and American firms: Is data

quality a way to extract business value?. Information & Management, 57(1), 103141. Retrieved from https://doi.org/10.1016/j.im.2019.01.003

Dai, H. N., Wang, H., Xu, G., Wan, J., & Imran, M. (2019). Big data analytics for manufacturing Internet of things: opportunities, challenges, and enabling tech-

nologies. Enterprise Information Systems, 1-25. Retrieved from https://doi.org/10.1080/17517575.2019.1633689

Dey, N., Hassanien, A. E., Bhatt, C., Ashour, A., & Satapathy, S. C. (Eds.). (2018). Internet of things and big data analytics toward next-generation intelligence

(pp. 3-549). Berlin: Springer. Retrieved from https://doi.org/10.1080/17517575.2019.1633689

3 3 3 3

12 12 13

7 7 14

3 7

15 15

12 12

9/14/2020 Originality Report

https://ucumberlands.blackboard.com/webapps/mdb-sa-BB5a31b16bb2c48/originalityReport/ultra?attemptId=33d3935c-b010-4d3a-a748-a6aedf709d7f&course_id=_… 3/6

Source Matches (32)

Student paper 89%

jkoolcloud 86%

Student paper 100%

Student paper 81%

Student paper 63%

Student paper 87%

Student paper 100%

Student paper

BIG DATA ANALYTICS 1 BIG DATA ANA- LYTICS 1

Original source

Big Data Science Analytics 1 Big Data Sci- ence Analytics 1

Student paper

Big Data Analytics and the Internet of Things

Original source

Big Data Analytics, healthcare, Internet of Things

Student paper

University of the Cumberland’s

Original source

University of the Cumberland’s

Student paper

ITS-836 Data Science & Big Data Analysis

Original source

ITS 836 Data Science and Big Data Analytics

Student paper

09/06/2020

Original source

06/28/2020

Student paper

With the evolution in the manufacturing industry, smart manufacturing is com- mon, and the Internet of Things plays a crucial role in connecting the physical as- pects of manufacturing to the digital space of decision-making algorithms and computing platforms.

Original source

During this evolution, Internet of Things plays an important role in connecting the physical environment of manufacturing to the cyberspace of computing plat- forms and decision-making algorithms, consequently forming a Cyber-Physical System

Student paper

There are many benefits associated with the IoT, such as reducing machine down- time, improving product quality, and im- proving factory production and operation.

Original source

reducing machine downtime, improving product quality and design, and improv- ing factory operations and productions

Student paper

The benefits of big data analytics in Man- ufacturing IoT includes;

Original source

Benefits of Big Data Analytics for Manu- facturing IoT

Student paper

Improving Product Quality.

Original source

Improving product quality

9/14/2020 Originality Report

https://ucumberlands.blackboard.com/webapps/mdb-sa-BB5a31b16bb2c48/originalityReport/ultra?attemptId=33d3935c-b010-4d3a-a748-a6aedf709d7f&course_id=_… 4/6

Student paper 75%

Student paper 67%

Student paper 74%

Student paper 100%

ProQuest document 78%

Student paper 100%

Student paper

Big data analytics, in this regard, offers solutions that are prescriptive, predictive, and descriptive, enabling companies to improve their product delivery, quality, and design, as well as after-sales support (Dai et al., 2019).

Original source

Customer satisfaction can be improved by big data analytics on customer data, which offers descriptive, predictive, and prescriptive solutions to enable compa- nies to improve product design, quality, delivery, warrant, and after-sales support (Dai et al., 2019)

Student paper

Data Representation Difficulties IoT oc- curs in different dimensions, heteroge- neous structures, and types. Since manu- facturing data can be categorized into unstructured, semi-structured, and struc- tured data, it poses a challenge for how exactly it should be represented under big data analytics (Ahmed et al., 2017).

Original source

Manufacturing of IoT data has different types, heterogeneous structures, and various dimensions For example, manu- facturing data can be categorized into structured data, semi-structured and un- structured data

Student paper

Consequentially, there is a need to intro- duce new storage paradigms that would support tremendously large data storage systems for big data analytics.

Original source

As a result, new storage paradigms need to be proposed to support large scale data storage systems for big data analytics

Student paper

Privacy and Security.

Original source

Privacy and security

Student paper

Ahmed, E., Yaqoob, I., Hashem, I.

Original source

Ahmed, E., Yaqoob, I., Hashem, I

Student paper

T., Khan, I., Ahmed, A.

Original source

T., Khan, I., Ahmed, A

Student paper

A., Imran, M., & Vasilakos, A.

Original source

A., Imran, M., & Vasilakos, A

Student paper

The role of big data analytics in the Inter- net of Things. Computer Networks, 129, 459-471.

Original source

The role of big data analytics in Internet of Things Computer Networks, 129, 459- 471

Student paper

Retrieved from https://doi.org/10.1016/j.comnet.2017.06 .013

Original source

Retrieved from https://doi.org/10.1016/j

Student paper

Bi, Z., & Cochran, D.

Original source

Bi, Z., & Cochran, D

9/14/2020 Originality Report

https://ucumberlands.blackboard.com/webapps/mdb-sa-BB5a31b16bb2c48/originalityReport/ultra?attemptId=33d3935c-b010-4d3a-a748-a6aedf709d7f&course_id=_… 5/6

Student paper 100%

Student paper 69%

Student paper 100%

hotpaper 100%

Student paper 100%

Student paper 93%

Student paper 100%

Student paper

Big data analytics with applications. Jour- nal of Management Analytics, 1(4), 249- 265.

Original source

Big data analytics with applications Jour- nal of Management Analytics, 1(4), 249- 265

Student paper

Retrieved from https://doi.org/10.1080/23270012.2014.9 92985

Original source

Retrieved from https://doi.org/10.1080/17517575.2019.1 633689

Student paper

Côrte-Real, N., Ruivo, P., & Oliveira, T.

Original source

Côrte-Real, N., Ruivo, P., & Oliveira, T

Student paper

Leveraging the Internet of things and big data analytics initiatives in European and American firms:

Original source

Leveraging internet of things and big data analytics initiatives in European and American firms

Student paper

Is data quality a way to extract business value?.

Original source

Is data quality a way to extract business value

Student paper

Information & Management, 57(1), 103141.

Original source

Information & Management, 57(1), 103141

Student paper

Retrieved from https://doi.org/10.1016/j.im.2019.01.003

Original source

https://doi.org/10.1016/j.im.2019.01.003

Student paper

N., Wang, H., Xu, G., Wan, J., & Imran, M.

Original source

N., Wang, H., Xu, G., Wan, J., & Imran, M

Student paper

Big data analytics for manufacturing In- ternet of things: opportunities, chal- lenges, and enabling technologies. Enter- prise Information Systems, 1-25.

Original source

Big data analytics for manufacturing in- ternet of things opportunities, challenges and enabling technologies Enterprise In- formation Systems, 1-25

Student paper

Retrieved from https://doi.org/10.1080/17517575.2019.1 633689

Original source

Retrieved from https://doi.org/10.1080/17517575.2019.1 633689

9/14/2020 Originality Report

https://ucumberlands.blackboard.com/webapps/mdb-sa-BB5a31b16bb2c48/originalityReport/ultra?attemptId=33d3935c-b010-4d3a-a748-a6aedf709d7f&course_id=_… 6/6

Student paper 100%

Student paper 100%12

Student paper

Dey, N., Hassanien, A. E., Bhatt, C., Ashour, A., & Satapathy, S.

Original source

Dey, N., Hassanien, A E., Bhatt, C., Ashour, A., & Satapathy, S

Student paper

Internet of things and big data analytics toward next-generation intelligence (pp.

Original source

Internet of things and big data analytics toward next-generation intelligence (pp

Student paper

Retrieved from https://doi.org/10.1080/17517575.2019.1 633689

Original source

Retrieved from https://doi.org/10.1080/17517575.2019.1 633689