Article Per Year (5 Year)
p-Index From 2021 - 2026
3.585
P-Index
This Author published in this journals
All Journal Informatika Journal of Computer Science and Information Systems (JCoInS) IKA BINA EN PABOLO : PENGABDIAN KEPADA MASYARAKAT Journal of Student Development Informatics Management (JoSDIM) Journal of Student Development Information System (JoSDIS)
Syaiful Zuhri Harahap
Sistem Informasi, Fakultas Sains dan Teknologi, Universitas Labuhanbatu
Aerospace Engineering Chemical Engineering, Chemistry & Bioengineering Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Education Environmental Science Library & Information Science Public Health Other

Published : 25 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 11 Documents
Search
Journal : informatika

 1   2 
Perancangan Aplikasi Panduan Belajar Gerakan Tunarungu Menggunakan Adobe Flash Ratna Juliani Siregar; Syaiful Zuhri Harahap
Jurnal Informatika Vol 10, No 2 (2022): INFORMATIKA
Publisher : Fakultas Sains & Teknologi, Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/informatika.v10i2.2981

Abstract

Deafness is one type of disability that is quite widely available in Indonesia, either experiencing it congenital or due to other factors where people with this disability experience a lack or loss of hearing ability so that they experience obstacles in language development. Deaf children still have the potential to learn to speak and speak. Therefore, deaf children need special services or media to develop language and speaking skills so as to minimize the impact of deafness experienced. Therefore, parents and teachers are obliged to guide children with hearing impairment to learn sign language. Currently, online education facilities are very attractive for children to learn. In fact, there are many developers who create modules, educational games, learning applications, tutorials, and more on Android. But not so for children with disabilities, especially deaf, Learning media is more likely to facilitate normal children. In fact, the learning materials and curricula of normal schools and special schools are the same, only the form of delivery is different. There are not many learning media for deaf children to learn, only the form of tutorials is limited to the introduction of the alphabet without any facilities to be able to deepen sign language itself. Deaf people need and deserve the same learning media as normal children.
Implementasi Data Mining Untuk Klustering Stunting Gizi Pada Balita Dipuskesmas Sigambal Meggunakan Metode K-Medoids Dan K-Means Melisa Melisa; Syaiful Zuhri Harahap; Masrizal Masrizal
Jurnal Informatika Vol 12, No 3 (2024): INFORMATIKA
Publisher : Fakultas Sains & Teknologi, Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/informatika.v12i3.6159

Abstract

The aim of this study was to identify and understand the different characteristics of toddlers in the context of factors that contribute to nutritional stunting. By using the clustering method, this study aims to group toddlers into several groups based on the similarity of their characteristics, so that more targeted interventions can be designed in dealing with stunting problems. Through this approach, it is hoped that significant patterns and risk factors can be found that distinguish stunted toddlers from toddlers who grow normally, and provide insights that can be used by policy makers and health practitioners to improve the quality of life of children. The method used in this study involves the application of two clustering techniques, namely K-Means and K-Medoids to Group sample data of 116 toddlers. The clustering process is carried out by measuring the distance between the toddler data and the centroid or medoid to determine which group is most suitable. The Data were analyzed to find patterns identifying unique characteristics of each cluster, reflecting differences in nutritional stunting-related risk factors.This process helps in differentiating groups of toddlers who are prone to stunting from those who are not, so that the analysis can be focused on the groups most in need of intervention. The results of clustering analysis showed that as many as 48 toddlers entered the C1 cluster, while the other 68 toddlers entered the C2 cluster. Each cluster describes two groups of toddlers with different characteristics in the context of nutritional stunting risk factors. The findings provide deep insight into the significant differences between the two groups, allowing researchers to identify specific patterns and risk factors. This information is then used to design more specific and effective interventions in addressing nutritional stunting in toddlers, taking into account the unique characteristics of each cluster that has been identified.
Application of Apriori and Fp-Growth Methods in Analyzing Book Lending Patterns Penerapan Metode Apriori dan Fp-Growth dalam Analisis Pola Peminjaman Buku Rahma Faradilah; Syaiful Zuhri Harahap; Irmayanti Irmayanti
Jurnal Informatika Vol 12, No 3 (2024): INFORMATIKA
Publisher : Fakultas Sains & Teknologi, Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/informatika.v12i3.6155

Abstract

Clustering of book borrowing patterns in the University of Labuhanbatu library aims to identify and understand student preferences and habits in borrowing books. With this analysis, the library can be more effective in managing book collections, ensuring the availability of frequently borrowed books, and improving the quality of service according to student needs. Using clustering techniques also helps in designing a more targeted book procurement strategy, so that existing resources can be optimally utilized to support the teaching and learning process. In this study, the methods used are Kf-Growth and Apriori to identify book borrowing patterns. Kf-Growth is used to find frequent itemsets or collections of books that are often borrowed together, while Apriori is used to generate association rules that reveal the relationships between borrowed books. Both of these methods allow for a more in-depth and comprehensive analysis of book borrowing patterns in the library, with the ability to handle large amounts of data and identify significant relationships between items. This process involves several stages, including data preprocessing, algorithm application, and evaluation of the results to ensure the validity and accuracy of the resulting clustering. The results of the clustering analysis show a very good confidence value, with many male and female students borrowing the book "Pengantar Akuntansi" consistently. This borrowing pattern shows that books related to economics and accounting have a high level of demand. The Kf-Growth and Apriori methods have proven to be very effective in clustering, providing accurate and reliable results. With these results, the Labuhanbatu University library can take more informative and strategic steps in managing book collections, ensuring that frequently borrowed books are always available, and improving the borrowing experience for students.
Simulasi Kinerja Karyawan di Kantor Pertanahan Labuhanbatu Menggunakan Algoritma C4.5 Khodijah Nasution; Masrizal Masrizal; Syaiful Zuhri Harahap
Jurnal Informatika Vol 12, No 3 (2024): INFORMATIKA
Publisher : Fakultas Sains & Teknologi, Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/informatika.v12i3.6160

Abstract

Employee performance analysis using the C4.5 algorithm in data mining aims to identify and classify employees based on their performance. The analysis process includes several stages, namely data analysis, preprocessing, model design in data mining, and method evaluation. From 47 sample data analyzed, the results show that 40 employees have good characters, while 7 employees have bad characters. Good employee characters are characterized by punctuality and high discipline in carrying out their duties. Conversely, bad employee characters are characterized by unpunctuality and low discipline, which have a negative impact on productivity and efficiency in the workplace. The results of this classification help identify areas that require more attention and intervention to improve overall employee performance. Model evaluation is carried out using two widgets, namely Test and Score and Confusion Matrix. The evaluation results of these two widgets show perfect accuracy of 100%. Meanwhile, the Confusion Matrix widget shows that all predictions are in accordance with the actual data without any errors in classification. These results confirm that the C4.5 algorithm is very effective and accurate in classifying employee performance. The perfection of the evaluation results shows that the C4.5 algorithm is very suitable for use as a classification model in employee performance analysis. The 100% accuracy of both widgets indicates that this algorithm is not only able to predict correctly but also consistently in various evaluation tools.
Analisis Minat Masyarakat Menggunakan Media Sosial Menggunakan Algoritma C4.5 dan Metode Naïve Bayes Nia Putri Panjaitan; Syaiful Zuhri Harahap; Rahma Muti Ah
Jurnal Informatika Vol 12, No 3 (2024): INFORMATIKA
Publisher : Fakultas Sains & Teknologi, Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/informatika.v12i3.6156

Abstract

The analysis of public interest using social media in data mining aims to understand user preferences and interests in various topics or products. By analyzing data from social media platforms, such as posts, comments, and interactions, researchers can identify significant interest patterns and trends, which can be used for more effective marketing strategies or product development that suits the public's desires. Common methods used in this analysis are the C4.5 and Naive Bayes algorithms. The C4.5 algorithm builds a decision tree that makes it easy to visualize and interpret the main factors that influence public interest. Meanwhile, Naive Bayes, with its probabilistic approach, classifies data based on existing features, providing fast and accurate predictions. Both methods are applied to process data from social media and produce in-depth insights into user preferences. The results of the analysis show that the prediction and classification of public interest have good accuracy, with the comparison result values showing very satisfactory performance. Both are able to identify and classify interests accurately, utilizing the advantages of each method to provide a better understanding of what is interesting to the public on social media.
Penerapan Data Mining Untuk Evaluasi Data Penjualan Menggunakan Metode Clustering Dan Agoritma Hirarki Divisive Studi Kasus Toko Sembako Pujo Ade Eka Febriyanti; Syaiful Zuhri Harahap; Masrizal Masrizal
Jurnal Informatika Vol 12, No 3 (2024): INFORMATIKA
Publisher : Fakultas Sains & Teknologi, Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/informatika.v12i3.6161

Abstract

The larger a company, the longer the company stands, the more companies have branches, of course, the greater the data owned. These data can be consumer data, purchase data, sales data, payroll data, and many other data. All data will usually be stored in a database. But many companies, even the Information Technology (IT) division, do not realize how valuable the pile of old data generated by the company in transactions and activities. Data mining is the study of methods for generating knowledge or finding patterns for processing data. So it's not just information, it's knowledge. Data Mining has several methods including clustering. Clustering is a well-known and widely used method in data mining. The main purpose of this clustering method is to Group a number of data/objects into clusters (groups) so that the cluster will contain the same data as each group. In this study, Divisive hierarchy algorithm is used to form clusters. From the pattern obtained is expected to provide knowledge for the company Media World Pekanbaru as a supporting tool to take policy.
Implementasi Data Mining Menggunakan Metode Algoritma FP-Growth Dan Algoritma Apriori Pada Toko IBR Jaya Untuk Meningkatkan Penjualan Restu Fauzy Naibaho; Syaiful Zuhri Harahap; Angga Putra Juledi
Jurnal Informatika Vol 12, No 3 (2024): INFORMATIKA
Publisher : Fakultas Sains & Teknologi, Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/informatika.v12i3.6128

Abstract

Dian trading business is one of the grocery stores engaged in buying and selling the main household needs of nine basic ingredients which have been doing a lot of grocery sales transactions. This transaction Data continues to grow every day and in the IBR Jaya store sales transaction data is only presented as an archive or report and it is not mentioned what the benefits of these data are. Nah, the problem at the IBR Jaya store is the improvement of improvements due to the shortage of basic food stocks that are often purchased by consumers are not available which results in improvements and usability improvements then the FP-Growth algorithm is used to analyze patterns of improvement and a priori algorithms for comparison through archived transaction data goods that will be purchased later as a reference to increase food stocks so as to increase sales at the IBR Jaya Food Store in the hope that this increase can help this is one of many ways to make money online. Association rules are a process in Data Mining to establish all associative policies that meet the minimum requirements for support (minsup) and trust (minconf) in a database . In association rules, there are 2 methods that can be used, namely a priori method and FP-Growth method. In this study the method used is FP-Growth algorithm and a priori algorithm, FP-Growth algorithm and a priori method is a method to find the most frequently appearing data set (frequent itemset) without using candidate generation that is suitable to analyze a data transaction.
Analisis Sistem Informasi Pengelolaan Data Alumni MAN Labuhanbatu Berbasis Codeigniter PHP Framework Muhammad Adlin Hasibuan; Syaiful Zuhri Harahap; Marnis Nasution
Jurnal Informatika Vol 12, No 3 (2024): INFORMATIKA
Publisher : Fakultas Sains & Teknologi, Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/informatika.v12i3.6157

Abstract

Alumni data management information system is a platform designed to manage and maintain alumni data effectively and efficiently. This system makes it easy for educational institutions to collect, store, and manage information about their graduates, such as personal data, education history, career, and their contribution to the alumni community. Using database technology and specialized software, the system enables fast data retrieval, organized data storage, and real-time monitoring of alumni activities. The existence of this information system also helps in maintaining good relations between institutions and alumni, as well as supporting alumni programs such as reunion events, networking, and career development. In addition, the alumni data Management Information System serves as a strategic tool in improving the quality and reputation of educational institutions. Research on alumni data management information system analysis using the CodeIgniter PHP framework as a programming language is interesting to do. CodeIgniter PHP Framework is known as one of the lightweight and efficient frameworks in web application development, so it can provide advantages in managing complex alumni data.
Implementasi Metode Naive Bayes dan Neural Network Untuk Menentukan Minat Masyarakat Pada Handphone Samsung Nelvi Nurrizqi M; Syaiful Zuhri Harahap; Irmayanti Irmayanti
Jurnal Informatika Vol 12, No 3 (2024): INFORMATIKA
Publisher : Fakultas Sains & Teknologi, Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/informatika.v12i3.6163

Abstract

Naive Bayes and Neural Network methods are used in analyzing people's interest in Samsung mobile phones to gain a better understanding of consumer preferences. Naive Bayes is a simple but very effective probability-based classification method. This method generates possible consumer interests by analyzing features such as price, specifications, and brands, and calculating the probability of different categories. Naive Bayes is very useful in situations where data has independent features, and can provide accurate results at high speed. By identifying patterns of people's preferences, this method can help Samsung adjust marketing and product strategies that are more in line with consumer needs. On the other hand, Neural Network offers more complex analytical capabilities by imitating the way the human brain works through a network of neurons. This method is used to process larger and more complex data in understanding consumer interest patterns in Samsung mobile phones. Neural Network can identify deeper relationships between various factors, such as the interaction between camera features and user needs, using deep learning processes. The purpose of using Neural Network is to capture nuances and trends that cannot be identified with simple methods, thereby providing a more comprehensive view of what drives consumer interest. The use of these two methods of analysis in public interest in Samsung mobile phones has provided very satisfactory results. The calculation values obtained from both methods show a high level of accuracy in the classification of consumer interest. The results of this analysis provide valuable insights for Samsung in understanding consumer preferences and needs, as well as helping the company in designing more effective products and marketing strategies. Thus, the combination of the use of Naive Bayes and Neural Networks not only provides stron g results, but also provides a more holistic approach to consumer data analysis.
Analisis Pola Pembelian Melalui Ponsel Menggunakan Algoritma Apriori dan Fp–Growth Pada Millenium Ponsel Nur Putri Andriani; Syaiful Zuhri Harahap; Irmayanti Irmayanti
Jurnal Informatika Vol 12, No 3 (2024): INFORMATIKA
Publisher : Fakultas Sains & Teknologi, Universitas Labuhanbatu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36987/informatika.v12i3.6158

Abstract

The purpose of this research is to understand the main factors that influence consumer decisions in purchasing the device. By exploring information about consumer preferences, needs, and behavior, this study seeks to identify purchasing trends and understand how aspects such as mobile phone features, price, and brand influence consumer choices. The main objective of this study is to provide in- depth insights to technology industry players so that they can develop more effective and relevant marketing and product strategies to meet dynamic market needs. To achieve this goal, this study uses the Apriori and FP-Growth methods, which are data mining algorithms that are effective in finding associations and patterns in transaction data. The Apriori method focuses on identifying the frequency of occurrence of itemsets and forming association rules based on support and confidence values, while FP- Growth uses a tree approach to store and extract frequently occurring patterns more efficiently. Both methods allow for in-depth analysis of mobile phone purchase data, so that complex patterns can be revealed more accurately and quickly. The results of this study indicate that there is a very clear mobile phone purchasing pattern among consumers, with confidence values reaching 90% for some association rules. For example, consumers who purchase phones with AMOLED displays tend to also choose large battery capacities from certain brands. These patterns indicate strong and consistent preferences across consumer groups, providing manufacturers with opportunities to target specific market segments with tailored product offerings. These findings not only provide valuable insights into consumer behavior but also help companies optimize their marketing strategies and increase their competitiveness in the technology industry.
Co-Authors Ade Eka Febriyanti Ade Parlaungan Nasution Akbar Madyan Angga Putra Juledi Bhakti Helvi Rambe Budianto Bangun Christine Herawati Limbong Dedi Naingolan Elfi Zahra Yuni Fasdiansyah Putra Fauziah Hanum Gafar Ilyaz JP Ibnu Rasyid Munthe Iin Kurniawati Dewi Indry Rizza Inny Rahayu Rambe Irmayanti Irmayanti Juli Hati Fitri Khairil Hanif Khodijah Nasution Lili Marliani Lisa Ariani Marnis Nasution Masitoh Ritonga Masrizal Masrizal Mei Lia Dani Harahap Melisa Melisa Mhd. Amin Muhammad Adlin Hasibuan Muhammad Irwansyah Hasibuan Mulya Rafika Nelvi Nurrizqi M Nia Edi Putri Nia Putri Panjaitan Nur Ainun Gulo Nur Putri Andriani Nurwahyunita Nurwahyunita Praida Hansyah Rahma Faradilah Rahma Muti Ah Ratna Juliani Siregar Restu Fauzy Naibaho Reyfo Irfankha Rinda Puspita Rista Andini Ritonga Rizky Maulana Sudi Suryadi Taufik Molid Hidayat Hasibuan Tiara Syavitri Rambe Zaitun Ritonga