Claim Missing Document
Check
Articles

Found 4 Documents
Search
Journal : Indonesian Journal of Applied Informatics

Implementasi Data Mining Penjualan Produk Pakaian Dengan Algoritma Apriori Anita Sindar RM Sinaga
IJAI (Indonesian Journal of Applied Informatics) Vol 4, No 1 (2019)
Publisher : Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (2379.962 KB) | DOI: 10.20961/ijai.v4i1.37989

Abstract

The problem faced by the Tanjung Redjo clothing store is the lack of management of sales data and irregular arrangement of clothing products. The arrangement of the location of clothing products on the shelf is not well regulated. The speed of service to customers can be improved by making the layout of clothing products good and orderly, so that store staff can find clothing products quickly. Shoppers can also search and view apparel accessories that are often sold together quickly, potentially increasing store sales turnover. A better and more organized arrangement of clothing products can be done by analyzing sales transactions that occur daily at the store by using the Apriori algorithm. By using this algorithm, the shop owner can find out the tendency of a combination of clothing products that are often sold at the same time, so that the shop owner can arrange the layout of clothing products well and regularly so that buyers or employees can find and retrieve clothing products quickly. How the Apriori algorithm works to find a combination of clothing products that are often sold simultaneously from a sales transaction. Rules applied If buying KA-701 and KK-201 and SP-2001, then buy ST-651. Support and Confidence values are calculated until 4 combination items are obtained to get the best selling associative rule output output.
Optimasi Asupan GGL Ideal Pada Usia Produktif Dengan Algoritma Genetika Anita Sindar RM Sinaga
IJAI (Indonesian Journal of Applied Informatics) Vol 4, No 2 (2020)
Publisher : Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20961/ijai.v4i2.41505

Abstract

Financial security encourages fast food eating habits, the characteristics of problems that require solving genetic algorithms that have multi-objective and multi-criteria. Based on the mathematical model built, an analysis is performed to find the best (optimal) solution. Optimization is an effort or activity to get the best results with the requirements given. Genetic Algorithm as a branch of Evolution Algorithm is an adaptive method commonly used to solve a value search in an optimization problem. To check the results of the optimization we need a fitness function, which signifies a coded description of the solution. During the process, the parent must be used for reproduction, crossing and mutation to obtain new offspring. Determination of the composition of the ideal GGL for productive age must meet the minimum limits for each component of nutrition. The higher the Fitness value the better the chromosomes become a candidate solution. Offspring results generated from the results of the reproduction process are crossever and mutation. The selection process is carried out to obtain the best chromosomes that will be made into the next generation's population. The best chromosomes  offSpring 10 Fitness 12737.34.
Sistem Deteksi Biometrik Keunikan Wajah Secara Real Time Anita Sindar RM Sinaga
IJAI (Indonesian Journal of Applied Informatics) Vol 4, No 1 (2019)
Publisher : Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1923.374 KB) | DOI: 10.20961/ijai.v4i1.35562

Abstract

Facial recognition is important for identifying a person's biodata profile. The physical development of students from the time they entered college to graduation has experienced inconspicuous changes but it is sometimes difficult to identify faces one by one. Digital form is becoming a trend to remember more real time. An important part of human physical identification has begun to shift from signature - finger - face selection. The face includes five important senses that are interconnected into an identification device. In this study the focus is on face detection based on color, the application of the Camshift Algorithm and finding the distance between the face sensing points is the result of the Gabor Wavelet method. Training data uses 4-8 second real time video. The hue histogram is basically the same as the RGB histogram, the difference is that the hue histogram uses the Hue value instead of RGB because the hue value represents natural color without regard to lighting. Gabor Wavelet transform is provided to solve filter design problems. The face detection system looks for face points to form a frame-shaped face selection if previously the face has been stored in a database so the system can easily describe biodata. Face selection can be done on live testing data. The selection box detection follows every facial movement.
Machine Learning Prediksi Karakter Pengguna Hastag (#) Bahasa Generasi Milenial Di Sosial Media Anita Sindar RM Sinaga
IJAI (Indonesian Journal of Applied Informatics) Vol 4, No 2 (2020)
Publisher : Universitas Sebelas Maret

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20961/ijai.v4i2.41764

Abstract

Activity on the internet leaves a traceable digital trail. Users who are expressive of social media and have a habit of pouring everything on Instagram are more considerate of the cause and effect of status updates. The problem discussed in this study is to describe the character of the Instagram user account according to the hashtags (#) of the most widely used millennial language such as #awesome and so on. With machine learning, computers can work alone. This digital technology has long been applied to Google search, search engines and social media (Facebook, Twitter, Instagram). The benefits of machine learning are the ease of obtaining digital data from online users. The stages of the study consisted of the application of algorithms that produced predictions for classification using the K-Nearest Neighbors Algorithm. The formulation of the problem in this research is how to process data sourced from millennial language hashtags based on the most popular hashtags (#) on instagram using machine learning by identifying names in the text into Connected, Creative and Confident. From the results of the calculation of the closest distance and proximity of the neighboring obtained 10 popular hashtags. Creative Classifications become dominan type user.