Hybrid of K-Means and partitioning around medoids for predicting COVID-19 cases: Iraq case study

Ali, Nidaa Ghalib; Abed, Saba Dhey; Shaban, Faris Ali Jasim; Tongkachok, Korakod; Ray, Samrat; Jaleel, Refed Adnan

doi:10.21533/pen.v9i4.2382

Cited by 9 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The distance is typically used to compare and contrast the characteristics of different data objects. The typical K-Means algorithm uses K = 2, meaning that it clusters data into pairs; when K equals 1, the K-Means algorithm in this study is enhanced, K's coordinates were found and then the nodes that form the cluster with K and those that are not in it were identified [23,24]. Given that we wish to search for a particular group of stores, the enhanced K-Means (EK-M) algorithm fits the concept of a market; the necessary product is available, and these stores are conveniently located; the location of customer represents the location of K. Based on the Euclidean Distance, the EK-M algorithm calculates the distance between two points.…”

Section: Enhanced K-means Clusteringmentioning

confidence: 99%

Retracted: Smart optimal path with blockchain modelling in internet of things using enhanced K‐means clustering and advance encryption standard

2023

View full text Add to dashboard Cite

The Internet of Things (IoT) were employed to help clients access the needed products with less effort and time. To discover the optimal path, enhanced K-Means (EK-M) clustering is utilised. By reducing the number of K from two or more to one, the conventional K-Mean has been improved. Using an IoTs platform, the optimal path should be the shortest distance. In EK-M, K is a telephone location, by using Global positioning systems sensor in a smart phone, latitude and longitude are used to detect the location of the phone, and Google Maps are used to find the locations of shops on a virtual map. The largest issue with IoT is security because of its complicated environment and the constrained resources of its devices. Blockchain is the main way that important information on IoT platforms is kept safe. In this study, the IoT framework using Blockchain with Advanced Encryption Standard (AES) in a six-block mode is protected. Products data is being encrypted, then transmitted to the Internet by means of an authorised person to be obtained from anywhere. To get at the sensors' actual readings, the decryption is finally proposed. In EK-M and AES, the suggested system yields good, secure, and balanced results. K E Y W O R D Scomputer network security, cryptography, data mining, internet of things | INTRODUCTIONThe IoT is a network that links individually identifiable computing devices, items, digital machines, mechanical devices, humans, and animals. Without computer or human-computer or human-human contact, this system may transport information [1]. IoT is a concept coined in 1999; internet-connected devices (whether wired or wireless). Reasons for Internet opportunity now and in the future are affordable gadgets, tiny, high-powered devices (sensors) of the order of millimetres or nanometres; these can operate on very little power [2]. The phrase "Internet of Things" is made up of two words: "Internet," which refers to protocols, communication, and networks; and "things," which refers to hardware components such as sensors and actuators [3]. The goal of the IoT is to improve people's lives by making everything in the world such as smart phone, smart TV, robots, motor vehicles, light bulbs, air conditioners, shelf space in your grocery store that are connected, monitored, actuating, and interacting among themselves without human intervention to perform actions that affect [4,5]. IoT is a solution that improves the medical outcome, make shopping safe and enjoyable, or make products faster, IoT entered in several domains [6]. Protecting the IoT network from security breaches is made easier with the use of blockchain technology. Blockchain is a distributed ledger technology that when used with the IoTs enables transactions to take place between machines. It makes use of a number of database-recorded transactions, validated by various means and recorded in a shared ledger accessible to all nodes [7]. IoT and blockchain work together to provide a number of potential advantages, including the ability for smart devices to operat...

show abstract

Section: Enhanced K-means Clusteringmentioning

confidence: 99%

Retracted: Smart optimal path with blockchain modelling in internet of things using enhanced K‐means clustering and advance encryption standard

2023

View full text Add to dashboard Cite

show abstract

“…According Ali et al (2021), BYJU'S inability to grow revenue hurt investors' confidence. As a result of persistent losses and uncertain growth prospects, the company's stock valuation suffered, making it harder to raise capital or attract top talent.…”

Section: Financial Situation Affects the Economymentioning

confidence: 99%

A case study of BYJU’S failure

Samrat Ray,

Kaviya Jain,

Piyush Birru

et al. 2024

World J. Adv. Res. Rev.

View full text Add to dashboard Cite

Once an education IT pioneer, BYJU'S, failure convoluted startup workers, investors. Byju failed due to financial mismanagement. Bad decisions and inconsistent financing prevented the corporation from paying its obligations. Company disagreements and leadership instability hurt BYJU'S operations. Due to negative press, BYJU'S brand suffers, its reputation suffered from data breaches, false advertising, and forced purchases. When the economy is terrible, earning more is tougher. These issues must be addressed for the future of technology. Businesses must be frugal, transparent, and financially aware. Customise marketing and market segmentation to accommodate everyone. Openness to new ideas and flexibility are needed to compete in a fast-changing market. Innovation, perseverance, and morality help Ed-tech overcome problems and capture opportunities. Businesses may learn from BYJU'S errors to grow sustainably, establish trust, and lead in the fast-paced, competitive educational technology business. Ed-tech must innovate after Byju failed. The company couldn't innovate; therefore, it struggled to compete and survive. Edtech companies must be inventive, customer-focused, and adaptable to compete in a competitive, ever-changing business. Learning from setbacks and encouraging resilience and creativity may help ed-tech companies thrive.

show abstract

“…The model recommended for the dataset was gathered using a questionnaire from 400 patients at several clinics in Iraq. When we compared the accuracy of the offered methods, we discovered that K-MP is more effective at determining a patient's state than K-Means and PAM, with an accuracy of 87.5% [15]; in 2019 Saru Subashree proposed a Decision Tree algorithm to detect a diabetic person with an accuracy of 94.44%. They employed three classification models: Decision Tree, K-nearest neighbors, and Naive Bayes.…”

Section: Literture Reviewmentioning

confidence: 99%

Hybrid K-means and Principal Component Analysis (PCA) for Diabetes Prediction

Abed Mohammed,

Sumari,

Attabi

2024

IJCDS

View full text Add to dashboard Cite

Diabetes is the "silent killer," stealing the lives of millions of people worldwide. There are many reasons for diabetes, such as increasing glucose, Cholesterol, systolic BP, and Age. These are considered to be the four primary causes of diabetes. The challenge in diabetes is predicting the human illness early to start treatment immediately after discovering diabetes; this can be the most challenging thing in diabetes discovery because tens of features may cause diabetes. This study proposes a model consisting of data mining and Machine Learning (ML) algorithms to predict if humans can have diabetes or not in the future. The prediction is made up of compensating two datasets; one dataset is used to reconfirm the other dataset in order to make a more accurate prediction. This can be performed using the k-means-PCA hybrid model and the highest weight selection of features that widely cause diabetes. The selected features help the ML algorithm predict the model's accuracy, which indicates the prediction model's accuracy. Simulation results show that the number of predict-diabetic patients increased from 53 from the original datasets to 142 after applying the proposed model. Simulation outcomes also prove that the Random Forest ML model gives the highest accuracy of other ML models, reaching 95.2%.

show abstract

Hybrid of K-Means and partitioning around medoids for predicting COVID-19 cases: Iraq case study

Cited by 9 publications

References 0 publications

Retracted: Smart optimal path with blockchain modelling in internet of things using enhanced K‐means clustering and advance encryption standard

Retracted: Smart optimal path with blockchain modelling in internet of things using enhanced K‐means clustering and advance encryption standard

A case study of BYJU’S failure

Hybrid K-means and Principal Component Analysis (PCA) for Diabetes Prediction

Contact Info

Product

Resources

About