Claim Missing Document
Check
Articles

Found 4 Documents
Search
Journal : Bulletin of Electrical Engineering and Informatics

Optimization of distance formula in K-Nearest Neighbor method Arif Ridho Lubis; Muharman Lubis; Al- Khowarizmi
Bulletin of Electrical Engineering and Informatics Vol 9, No 1: February 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (610.331 KB) | DOI: 10.11591/eei.v9i1.1464

Abstract

K-Nearest Neighbor (KNN) is a method applied in classifying objects based on learning data that is closest to the object based on comparison between previous and current data. In the learning process, KNN calculates the distance of the nearest neighbor by applying the euclidean distance formula, while in other methods, optimization has been done on the distance formula by comparing it with the other similar in order to get optimal results. This study will discuss the calculation of the euclidean distance formula in KNN compared with the normalized euclidean distance, manhattan and normalized manhattan to achieve optimization results or optimal value in finding the distance of the nearest neighbor.
The effect of a SECoS in crude palm oil forecasting to improve business intelligence Al-Khowarizmi Al-Khowarizmi; Ilham Ramadhan Nasution; Muharman Lubis; Arif Ridho Lubis
Bulletin of Electrical Engineering and Informatics Vol 9, No 4: August 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (561.401 KB) | DOI: 10.11591/eei.v9i4.2388

Abstract

Crude palm oil is a crop that has a harvest period of ± 2 weeks and is in dire need of dissemination of information using e-commerce in order to be able to predict the price of the yield of companies or individual gardens within the next 2 weeks in order to improve studies on business intelligence. The disadvantage of not implementing e-commerce is certainly detrimental to the garden owner because they have to go through an agent so prices are set based on the agent. So with the application of e-commerce, buyers of crude palm oil can predict prices in conducting business processes to the future. So the need to forecasting the price of crude palm oil heads in order to improve the application of business intelligence using the evolution-based artificial neural network (ANN) method which in this paper is tested with SECoS get a MAPE value of 0.035% and by applying business intelligence can protect transaction costs by 33.3%.
Human blood group type detection prototype focusing on agglutinin using microcontroller based photodiode Lubis, Arif Ridho; Harefa, Hafid Rahman; Al-Khowarizmi, Al-Khowarizmi; Julham, Julham; Lubis, Muharman; Rahmat, Romi Fadillah
Bulletin of Electrical Engineering and Informatics Vol 13, No 4: August 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v13i4.7007

Abstract

Blood is a fluid in the body that mainly serves as a medium for transporting various substances in the body. Detection of human blood group types with this microcontroller utilizes dark and light properties. The dark character appears due to agglomeration, while the light nature arises because of no agglomeration, for this to happen, a liquid reagent is needed. Administration of this liquid uses the aviator's breathing oxygen (ABO) system, which consists of reagent a, reagent b, and reagent c and mixing it with blood on the test paper. The number of blood samples in each reagent is based on blood lancet. Furthermore, the sensors used to detect these properties are photodiode and light emitting diode (LED) each of 3 pieces. The Arduino Uno is used to process sensor input while at the same time producing displayed human blood group type on the display screen. The test is carried out involving 12 blood samples and a medical officer. Medical officer are tasked reading directly the results of mixing between reagents and blood samples, after that are compared with the system. The results show that the deviation of the system reading is 0.167 for the sensor reading distance with the sample as far as 0.5 cm.
Braille letter recognition in deep convolutional neural network with horizontal and vertical projection Rahmat, Romi Fadillah; Purnamawati, Sarah; Mardianto, Willy; Faza, Sharfina; Sulaiman, Riza; Nadi, Farhad; Lubis, Arif Ridho
Bulletin of Electrical Engineering and Informatics Vol 13, No 5: October 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v13i5.7222

Abstract

Brail is a written mode of communication utilized by individuals with visual impairments to engage in interpersonal exchanges. The braille writing system consists of patterns printed on specialized paper that feature embossed dots. Braille documents enable the visually impaired to acquire knowledge and information exclusively through the application of their sense of contact. Comprehending braille is not a simple undertaking, particularly for the general populace. Because braille is not a required subject in Indonesian education, the majority of the population lacks proficiency in the language. This may therefore result in a minor communication barrier between visually impaired individuals and non-impaired individuals. In order to address this challenge, the present study employs digital image processing via the deep convolutional neural network (DCNN) technique to facilitate comprehension of braille document contents by non-braille speakers. This study employs a deep learning technique that is highly accurate, effective at image processing, and capable of recognizing complex patterns. This study employed the following image processing methods: grayscaling, filtering, contrast enhancement, thresholding, morphological operation, and resizing. Following testing in this investigation, it was determined that the proposed method accurately identifies embossed braille images with a precision of 99.63%.