cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Paska Hasugian
Contact Email
infokum@seaninstitute.org
Phone
+6281264451404
Journal Mail Official
infokum@seaninstitute.org
Editorial Address
Komplek New Pratama ASri Blok C, No.2, Deliserdang, Sumatera Utara, Indonesia
Location
Unknown,
Unknown
INDONESIA
INFOKUM
Published by SEAN INSTITUTE
ISSN : 23029706     EISSN : 27224635     DOI : -
Core Subject : Science,
Computer Science & IT
The INFOKUM a scientific journal of Decision support sistem , expert system and artificial inteligens which includes scholarly writings on pure research and applied research in the field of information systems and information technology as well as a review-general review of the development of the theory, methods, and related applied sciences. Software Engineering. Image Processing Datamining Artificial Neural Networks
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 842 Documents
 7   8   9   10   11 
DUAL TREE HUFFMAN ENCODING IMPLEMENTATION TO REDUCE LOW FREQUENCY BIT CODES Tommy Tommy
INFOKUM Vol. 9 No. 2, June (2021): Data Mining, Image Processing and artificial intelligence
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (261.016 KB)

Abstract

Huffman encoding is a compression algorithm that uses symbol encoding using a simpler bit substitution based on the frequency of the symbol. A symbol will be represented with much fewer bits if it has a large frequency. Conversely, symbols with less frequency will be encoded with bits of greater length. The bit code for symbols with lower frequencies often has a very long size which sometimes causes the compressed file size to be larger than the original file. This study develops the implementation of two separate Huffman trees by dividing the symbol list into two lists, each of which will form a bit code in parallel. This implementation is able to minimize the length of the symbol bit code, especially in symbols with low frequencies so as to increase the compression ratio for several types of content which is become the weakness of the original Huffman.
Capacity Optimization On RGB Overlapping Block-Based Pixel Value Differencing Image Steganography With Adaptive Threshold Rosyidah Siregar
INFOKUM Vol. 9 No. 2, June (2021): Data Mining, Image Processing and artificial intelligence
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (409.052 KB)

Abstract

Pixel value differencing steganography is an image steganography that utilizes the difference of the image pixel value to embed the secret message bits. RGB overlapped block-based PVD was introduced by Prasad and Pal which uses the difference value in the pair of RGB color components of a pixel compared to using the difference value of two consecutive pixels. This approach has good performance at increasing capacity especially in images with low pixel variance values. The RGB overlapped block-based PVD algorithm uses a threshold that limits the amount of difference in the color component pairs that are allowed to embed the secret message bits. The use of a global threshold will reduce the potential for optimal capacity utilization of the container image. This study implements an adaptive threshold that uses two different types of thresholds that use the embedding bit limit and the RMSE difference of the pixels before and after the embedding process to the next pixel. This optimization is able to provide a better capacity increase with PSNR degradation from the previous algorithm which is quite low.
Implementation of Topsis Method for Supervisor Selection Decision Making System at District 10 Restaurant And Bar Emasopangidoan Waruwu Emasopangidoan
INFOKUM Vol. 9 No. 2, June (2021): Data Mining, Image Processing and artificial intelligence
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (337.042 KB)

Abstract

Management of Resources Manuasion of a company greatly influences many aspects of determining the success of the company. If the company's performance can be organized, all aspects of the company can run Good. The problem in District 10 Restaurant And Bar in choosing a supervisor is to use measurements based on the aspects and criteria desired and achieved by the company. So that in the process of selecting the pervisor only based on the direct behavior that is considered senior, but there is a fact that it cannot contribute more to the company and there is no specific method used in selecting Supervisors, so that the assessment is not appropriate. To overcome this problem, a computer system is needed that helps the Supervisor by using the Topsis Method TOPSIS (Technique for Others Reference to Ideal Solution). It will rank all alternatives to positive alternative solutions that have been ranked and then used as a reference for decision making, namely decision support system takes the decision to choose the best solution that is desired.
COMPUTER VISION IDENTIFICATION OF SPECIES, SEX, AND AGE OF INDONESIAN MARINE LOBSTERS Yasir Hasan; Kristian Siregar
INFOKUM Vol. 9 No. 2, June (2021): Data Mining, Image Processing and artificial intelligence
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (541.459 KB)

Abstract

Lobster in Indonesia consists of various types of colors, shapes, and habitats. Documentation results from several studies in the field of fisheries show the dynamics and richness of this type of shrimp species that have a hard and large skeleton. It is necessary to apply this knowledge to the field of information technology and computerization. The application that is right on target for the community is the application that is felt to be useful in the activities of the community itself. The application of information on lobster diversity found in Indonesia in the form of computer technology is to create a knowledge-based lobster recognition computer. This computer technology is designed as a computer vision identification of species, sex, and age of Indonesian water lobsters. Lobster identification is built with three levels of structure, namely the introduction of the type of lobster, the introduction of the sex of the lobster, and the introduction of the age of the lobster. The identification of lobster species here uses color recognition and edge detection techniques from lobster body image data that has been stored in a python-based value library file. For gender recognition using edge detection and pattern recognition techniques from image data of the bottom of the lobster such as the image of the legs. Meanwhile, for the introduction of lobster age, the technique of measuring the length of the lobster carapace distance was used. All these objects can be identified by the features provided by OpenCV in Python language
EXAMINE THE ROLE OF MOTIVATION IN UTAUT MODEL ON THE USE OF CLOUD COMPUTING BY SMEs DURING COVID-19 PANDEMIC Marwan Al Fajri; Erwin Setiawan Panjaitan; Hanes Hanes
INFOKUM Vol. 9 No. 2, June (2021): Data Mining, Image Processing and artificial intelligence
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (374.957 KB)

Abstract

The 2019 Corona Virus Disease (COVID-19) pandemic is affecting the business sector in Indonesia, especially Small and Medium Enterprise (SMEs) that contribute greatly to the economy which impacted on decrease in revenue due to health protocols. This study aims to examine the role of motivation in the use of cloud computing technology by SMEs during the pandemic by combining it with the Unified Theory of Acceptance and Use of Technology (UTAUT) model. The research method uses quantitative data to test hypotheses that have been formulated through a survey of 129 SMEs in Medan using cloud computing technology since the pandemic. Questionnaires are distributed online and offline containing 25 indicators of variables arranged using the Likert scale. The data processing in this study used equation models from Structural Equation Modeling (SEM) and Smart Partial Least Square (SmartPLS) software. The results of this study received a positive response and showed a significant influence on motivation variable. SME actors have the motivation to survive in the sustainability of their business by using cloud computing technology as a necessity. So that the effect on the intention to use (behavior intention) to use cloud computing technology affects the actual use by SMEs.
COMBINATION OF K-MEANS CLUSTERING AND K-NEAREST NEIGHBOR ON ECOMMERCE CUSTOMER SPENDING RATE PREDICTION Boni Octaviana
INFOKUM Vol. 9 No. 2, June (2021): Data Mining, Image Processing and artificial intelligence
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (316.125 KB)

Abstract

K-Nearest Neighbor is a classification method that classifies new data into specific classes based on the proximity of characteristics to k members of existing classes. K-Nearest Neighbor relies heavily on training data. In actual circumstances such as the ecommerce customer spending rate dataset, there is no class label for each data. So that to be able to obtain datatraining required additional methods need to be added before the prediction process can be done. This research attempts to use K-Means Clustering to group datasets into multiple clusters which then each cluster will be given a class label according to the centroid characteristics of those clusters. The combination of KNN and K-Means Clustering methods in customer's spending rate predictions gives a fairly good result, where the accuracy of the prediction obtained is 89.6%.
Application of Multi-Objecttive Optimazation on the basis of Ratio Analysis in Determining Monthly Study Agenda onMasjid Al-Muhajirin Rumah Pondok Mansion Saidi Ramadan Siregar; Pristiwanto Pristiwanto
INFOKUM Vol. 9 No. 2, June (2021): Data Mining, Image Processing and artificial intelligence
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (418.91 KB)

Abstract

Pondok Mansion House (RPM) which is located in the Namorambe sub-district, Deli Serdang Regency is one of the government subsidized housing held by PT Rapy Ray. The construction of the mosque which has been completed provides good news for the Muslim residents of the housing because they can carry out routine prayers and various other Islamic holiday activities. On Saturday, June 19, 2021, a mosque committee was formed before the establishment of the Mosque Prosperity Agency. Then after the mosque committee was formed. The mosque committee held a meeting to find the name of the mosque and to complete the management of the mosque which was held on July 7, 2021. To make the mosque agenda, it was discussed again by inviting members of the management which coincided on August 3, 2021. Then the results of the meeting were agreed upon by the mosque management and the problem that occurs is the emergence of disagreements or disagreements on one of the mosque's agenda schedules resulting in small talks in the housing complex area which can result in disorganization between mosque administrators and individuals who do not agree with the agenda. It is necessary to make a policy in preparing a schedule with a scientific system based on mathematical calculations so that the results can provide explanations and can be accepted with grace. Of course the well-known system in this case is the Decision Support System (DSS) in which this system provides suggestions, input, as well as contributions to organizational actors, associations whose nature is to choose the best among several available options. Then the results will provide solutions in the form of approaches with alternative systems, ratings and several components related to DSS. The value of the approach or result that will be given later reaches 80% to 95%..
Testing C4.5 Algorithm Using Rapid Miner Applications In Determining Customer Satisfaction Levels Fithrie Soufitri; Ellanda Purwawijaya; Eka Hayana Hasibuan; Roy Nuary Singarimbun
INFOKUM Vol. 9 No. 2, June (2021): Data Mining, Image Processing and artificial intelligence
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (308.415 KB)

Abstract

Data mining is a series of processes to extract added value in the form of information that has not been known manually from a database. The resulting information is obtained by extracting and recognizing important or interesting patterns from the data contained in the database. One part of the service of an agency is the service to customers, customers or those related to certain services. The quality of service is assessed by what has been done and how to treat from those who serve, some provisions used to ensure service optimization are Confiden, Integrity, Pride and Passion with the main purpose or output is Customer Satisfaction. The process of Forming a Pattern of Satisfaction Level by Utilizing the C4.5 Algorithm Penelitain process is carried out by data collection, testing with applications, exposure of pattern results or Knowledge. Pola yang terbentuk after the extraction is 1.Integrity = low: quite satisfied {very satisfied=0, quite satisfied=3}Integrity = tall, Passion = low: quite satisfied {very satisfied =0, quite satisfied =2}, Passion = tall: very satisfied {very satisfied =11, quite satisfied =0}.
IMPLEMENTATION OF TF-IDF AND COSINE SIMILARITY ALGORITHMS FOR CLASSIFICATION OF DOCUMENTS BASED ON ABSTRACT SCIENTIFIC JOURNALS Paska Marto Hasugian; Jonson Manurung; Logaraz Logaraz; Uzitha Ram
INFOKUM Vol. 9 No. 2, June (2021): Data Mining, Image Processing and artificial intelligence
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (503.77 KB)

Abstract

Research on one of the higher education dharmas is carried out by each lecturer and is a challenge for lecturers who pay attention to produce new and useful findings. Research results will be published in journals both nationally and internationally and one of the websites published by Ristekbirn is Sinta which includes all research works in Indonesia. The problem in this research is the accumulation of data that is getting bigger and it needs to be analyzed by utilizing text mining by searching for the resources contained in the abstract document and presenting part of the information. The purpose of this study is to classify the suitability of another document so that knowledge is found. and placement in groups according to existing topics. The process of these problems is by classifying documents based on abstracts from the publication of scientific papers. Solving these problems involves two mutually supporting algorithms, namely TD-IDF with Cosine Similarity with different tasks. TF-IDF ensures the weight of each document that can be read and read with Cosine Similarity. This research uses text mining as part of the search for related patterns and documents that have been tested. For the process of calculating the test data, 1 document and 15 documents were used as training data. With the calculation of TD-IDF the weight of each document from Q, D2 to D15 is 10,946, 28,050,27,176, 39,043, 36,535, 30,696, 25,612, 12,581, 42,335, 29,661, 33,867, 31,706, 22,654, 15,450, 59,832, 42,127, The similarity of the data is tested by determining the value of k = 4 which results in similarity to the Expert System and Cryptography, while with the selection of K = 5 with the highest similarity to the expert system..
Linear Regression Analysis To Predict The Length Of Thesis Completion Fristi Riandari; Hengki Tamando Sihotang
INFOKUM Vol. 9 No. 2, June (2021): Data Mining, Image Processing and artificial intelligence
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (2060.102 KB)

Abstract

Students who carry out knowledge in the undergraduate program will certainly be faced with the preparation of a thesis at the end of their study period. However, every year students still find it takes longer than the time specified in completing their thesis. This is caused by several things, such as students who are working, working hours that do not support the implementation of thesis preparation, students who already have families and other factors. This of course makes universities have to prepare special strategies in order to reduce the number of students who cannot complete their thesis on time in the future, one of which is with a decision support. This can be done by utilizing university big data. Prediction of the length of time for completion of college student thesis can be done by utilizing data mining and a simple linear regression approach. Using 1 independent variable, namely the average inhibiting factor (Working Status, Working Hours, Work Sip, Guidance Media, Status) (X1) and the number of days of thesis completion being the dependent variable (Y). After looking for the regression value of b and constant a, then the simple linear regression equation model is: Y = 280.450 + 1.650 X.

Page 9 of 85 | Total Record : 842

 7   8   9   10   11 

Filter by Year

2018 2026


Reset
Filter By Issues
All Issue Vol. 14 No. 02 (2026): Infokum, March-April 2026 Vol. 14 No. 01 (2026): Infokum, January - February 2026 Vol. 13 No. 06 (2025): Infokum Vol. 13 No. 05 (2025): Infokum Vol. 13 No. 04 (2025): Infokum Vol. 13 No. 03 (2025): Infokum Vol. 13 No. 02 (2025): Infokum Vol. 13 No. 01 (2025): Infokum Vol. 12 No. 04 (2024): Engineering, Computer and Communication, November 2024 Vol. 12 No. 01 (2024): Engineering, Computer and Communication, Edition January 2024 Vol. 11 No. 05 (2023): Engineering, Computer and Communication Vol. 11 No. 04 (2023): Agustus : Engineering, Computer and Communication Vol. 11 No. 03 (2023): Juni : Engineering, Computer and Communication Vol. 11 No. 02 (2023): April, Engineering, Computer and Communication Vol. 10 No. 03 (2022): August, Data Mining, Image Processing, and artificial intelligence Vol. 10 No. 02 (2022): Juni, Data Mining, Image Processing, and artificial intelligence Vol. 10 No. 5 (2022): December, Computer and Communication Vol. 10 No. 4 (2022): October, computer, information and engineering Vol. 10 No. 1 (2021): Desember, Data Mining, Image Processing, and artificial intelligence Vol. 9 No. 2, June (2021): Data Mining, Image Processing and artificial intelligence Vol. 9 No. 1,Desember (2020): Data Mining, Image Processing,artificial intelligence, networking Vol. 8 No. 2, Juni (2020): Data Mining, Image Processing and artificial intelligence Vol. 8 No. 1, Desembe (2019): Data Mining,Image Processing and artificial intelligence Vol. 7 No. 2, Juni (2019): Data Mining And Image Processing Vol. 7 No. 1, Desembe (2018): Data Mining And Image Processing More Issue