frequent pattern
Recently Published Documents


TOTAL DOCUMENTS

1048
(FIVE YEARS 291)

H-INDEX

32
(FIVE YEARS 5)

Sebatik ◽  
2022 ◽  
Vol 26 (1) ◽  
Author(s):  
Irwan Adji Darmawan ◽  
Muhammad Fakhri Randy ◽  
Imam Yunianto ◽  
Muhamad Malik Mutoffar ◽  
M Tio Putra Salis

Penyandang Masalah Kesejahteraan Sosial (PMKS) menjadi satu dari sekian masalah yang terdapat di daerah perkotaan, sebab dapat mengganggu pembangunan kota, ketertiban umum, keamanan dan stabilitas. Sejauh ini langkah yang dilakukan sementara masih terfokus dengan cara penanganan PMKS, masih belum mengarah untuk mencegah. Menentukan pola golongan PMKS merupakan salah satu cara yang dapat dilakukan. Algoritma Apriori memiliki fungsi untuk membantu menemukan pola yang terdapat pada data (frequent pattern mining) untuk menentukan frequent itemset yang menggunakan metode Association Rule dalam data mining. Dalam penghitungan secara manual yang dilakukan maka didapat pola kombinasi antara lain 3 rules yang memiliki nilai minimum support 15% dengan confidence tertinggi 100% menggunakan Algoritma Apriori. Dalam menguji Algoritma Apriori digunakan aplikasi RapidMiner. RapidMiner merupakan satu dari beberapa software pengolah data mining, misalnya menganalisis teks, mengekstrak pola data set kemudian dikombinasikan menggunakan metode statistik, database, dan kecerdasan buatan agar didapat informasi yang tinggi berasal dari olahan data. Hasil yang didapat dari pengujian perbandingan pola antar golongan PMKS. Dari pengujian menggunakan aplikasi RapidMiner dan penghitungan secara manual Algoritma Apriori, maka disimpulkan dengan kriteria pengujian, bahwa pola (rules) golongan dengan nilai confidence (c) penghitungan manual Algoritma Apriori dapat dibilang tidak mendekati hasil pengujian aplikasi RapidMiner, maka dapat dikatakan tingkat keakuratan pengujian rencah, hanya 37,5%.


Author(s):  
Subrata Datta ◽  
Kalyani Mali ◽  
Sourav Das ◽  
Srijita Kundu ◽  
Sayanta Harh

2022 ◽  
pp. 1-12
Author(s):  
Jingyi Li

Traditional financial data storage methods are prone to data leakage and narrow data coverage. Therefore, this paper proposes a dynamic and secure storage method of financial data based on cloud platform.In order to improve the ability of enterprise data management, the paper constructs a financial cloud computing platform, mining financial data by rough set theory, and analyzing the results of frequent pattern mining of financial data by fuzzy attribute characteristics.According to the granularity theory, the financial data is classified and processed, and the CSA cloud risk model is established to realize the dynamic and secure storage of financial data.The experimental results show that. The maximum data storage delay of this method is no more than 4.1 s, the maximum data leakage risk coefficient is no more than 0.5, the number of data types can reach 30, and the data storage coverage is improved.


Rekayasa ◽  
2022 ◽  
Vol 14 (3) ◽  
pp. 456-460
Author(s):  
Paisal Soleh ◽  
Abu Tholib ◽  
M. Noer Fadli Hidayat

Author(s):  
Aleardo Junior Manacero ◽  
Renata Spolon Lobato ◽  
Marcos Antônio Cavenaghi ◽  
Alexandre Colombo ◽  
Roberta Spolon

2022 ◽  
pp. 21-70
Author(s):  
Hiren Kumar Thakkar ◽  
Hrushikesh Shukla ◽  
Prasan Kumar Sahoo

2022 ◽  
pp. 116435
Author(s):  
Meserret Karaca ◽  
Michelle M. Alvarado ◽  
Mostafa Reisi Gahrooei ◽  
Azra Bihorac ◽  
Panos M. Pardalos

2021 ◽  
Vol 2021 ◽  
pp. 1-17
Author(s):  
Jing Chen ◽  
Peng Li ◽  
Weiqing Fang ◽  
Ning Zhou ◽  
Yue Yin ◽  
...  

Real-time data stream mining algorithms are largely based on binary datasets and do not handle continuous quantitative data streams, especially in medical data mining field. Therefore, this paper proposes a new weighted sliding window fuzzy frequent pattern mining algorithm based on interval type-2 fuzzy set theory over data stream (WSWFFP-T2) with a single scan based on the artificial datasets of medical data stream. The weighted fuzzy frequent pattern tree based on type-2 fuzzy set theory (WFFPT2-tree) and fuzzy-list sorted structure (FLSS) is designed to mine the fuzzy frequent patterns (FFPs) over the medical data stream. The experiments show that the proposed WSWFFP-T2 algorithm is optimal for mining the quantitative data stream and not limited to the fragile databases; the performance is reliable and stable under the condition of the weighted sliding window. Moreover, the proposed algorithm has high performance in mining the FFPs compared with the existing algorithms under the condition of recall and precision rates.


Sign in / Sign up

Export Citation Format

Share Document