Claim Missing Document
Check
Articles

Found 28 Documents
Search

Pelatihan Datascience pada Pra-Pemrosesan Data untuk Siswa SMK Media Informatika - Jakarta Hasanudin, Muhaimin; Dwiasnati, Saruni; Gunawan, Wawan
Jurnal Pengabdian Pada Masyarakat Vol 9 No 4 (2024): Jurnal Pengabdian Pada Masyarakat
Publisher : Universitas Mathla'ul Anwar Banten

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30653/jppm.v9i4.921

Abstract

Pengabdian Kepada Masyarakat (PKM) merupakan upaya untuk melengkapi siswa dengan keterampilan yang relevan dalam teknologi informasi. Meskipun kurikulum perguruan tinggi telah menekankan pada teknologi dan ilmu komputer, kurangnya pemahaman tentang data science dan pra-pemrosesan data masih menjadi masalah. PKM ini tidak hanya mengajarkan penggunaan alat seperti Python tetapi juga mendorong pemikiran analitis dan kritis saat menganalisis data. Proses pra-pemrosesan data, termasuk normalisasi dan penanganan outlier, berdampak langsung pada input data model machine learning. PKM berfokus pada pelatihan siswa SMK Media Informatika dalam machine learning dan eksplorasi perubahan pada data masukan untuk mempengaruhi akurasi model, melalui serangkaian eksperimen menggunakan berbagai jenis dataset, program ini menganalisis bagaimana modifikasi pada data dapat mempengaruhi performa model pembelajaran mesin. Tujuan PKM adalah meningkatkan pemahaman siswa tentang pentingnya pra-pemrosesan data dalam mencapai model machine learning yang akurat. Evaluasi keberhasilan PKM melibatkan peningkatan pemahaman siswa, pengembangan keterampilan praktis, dan umpan balik positif. Pelatihan PKM berhasil meningkatkan pemahaman peserta dengan jumlah yang tidak mengerti berkurang dari 3,3% menjadi 0% setelah post-test. Persentase peserta yang mengerti materi meningkat dari 46,7% menjadi 60%. Community service is an effort to equip students with relevant skills in information technology. Although the college curriculum has emphasized technology and computer science, the lack of understanding of data science and data Pre-Processing is still an issue. Community service not only teaches the use of tools such as Python but also encourages analytical and critical thinking when analyzing data. Data Pre-Processing, including normalization and outlier handling, has a direct impact on the input data of machine learning models. The Community Service focuses on training SMK Media Informatika students in machine learning and exploring changes to the input data to affect model accuracy. Through a series of experiments with varied datasets, the Community Service analyzes the effect of changes to the data on model performance. The aim of the project was to improve students understanding of the importance of data Pre-Processing in achieving accurate machine learning models. The project's success was evaluated based on increased student understanding, practical skill development, and positive feedback. PKM training succeeded in improving participants' understanding with the number of those who did not understand decreasing from 3.3% to 0% after the post-test. The percentage of participants who understood the material increased from 46.7% to 60%.
Penilaian Kualitas Quality of Service Jaringan Internet WLAN PT. Solid Fintek Indonesia Rizky, Muhammad; Dwiasnati, Saruni
JATISI Vol 11 No 4 (2024): JATISI (Jurnal Teknik Informatika dan Sistem Informasi)
Publisher : Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/jatisi.v11i4.8205

Abstract

This research focuses on analyzing QoS (Quality of Service) on the internet network of PT. Solid Fintek Indonesia. Quality of Service is used as an analysis method to measure the quality of internet network services, the information from which can be input to improve disturbances that often occur on the network of PT. Solid Fintek Indonesia, such as sudden network slowdowns, lag that results in communication disruption, and loss of Wi-Fi network. In this study, the analysis was conducted using QoS parameters, including throughput, delay, jitter, and packet loss. Wireshark was used as a tool to scan and record internet traffic. The main objective of this research is to provide valuable insights for improving the performance of WLAN networks at PT. Solid Fintek Indonesia and similar organizations. By understanding the factors of network quality, it is hoped to find an effective solution to improve performance network. The results of testing the WLAN network based on TIPHON standardization at PT. Solid Fintek Indonesia show an index value on the throughput parameter of 2390 Kbps with the category “Very Good”, delay of 4,13 ms with the category “Very Good”, jitter of 4,13 ms with the category “Good”, and packet loss of 2,67 % with the category “Very Good”.
Daur Ulang Sampah Anorganik di Cengkareng Jakarta Barat Yuliarty, Popy; Utami, Diah; Dwiasnati, Saruni
IRA Jurnal Pengabdian Kepada Masyarakat (IRAJPKM) Vol 2 No 3 (2024): Desember
Publisher : CV. IRA PUBLISHING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56862/irajpkm.v2i3.151

Abstract

This PkM activity was intended to increase knowledge and skills in managing inorganic waste at partner locations and their surroundings. That problem can be overcome by providing education, understanding the importance of sorting waste from home to public places, for example, at school, providing insight into the value that this waste still has from an economic perspective and providing training in skills to make recycled products from the collected waste. The method for this activity begins with observation at the location, preparation, and implementation in two extensive sessions, namely providing theoretical material and practical material for making recycled products. Participants were asked to fill out a questionnaire to assess their activity. The expected output is a product resulting from recycling plastic wrap waste and showing appreciation to participants for the best-recycled products. Coming from the description of the situation review, the PkM team concluded that there were several problems faced by Mitra, namely: Mitra is a place that has the potential to produce large amounts of inorganic waste because of the enormous of students, and it is located in a very dense residential area, very close together. Also, with the Cengkareng Big Market, efforts need to be made to manage waste, especially inorganic waste, by recycling inorganic waste into value-added products.
Penerapan Clustering dalam Data Science Untuk Mengembangkan Keterampilan Analitik di SMK Media Informatika Eliyani, Eliyani; Rifqi, Muhammad; Dwiasnati, Saruni
Jurnal Pengabdian Masyarakat Vol. 3 No. 2 (2024): Desember 2024
Publisher : Unity Academy

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70340/japamas.v3i2.162

Abstract

The current and future job market requires a workforce skilled in data science, including analytical techniques such as clustering. With the development of Industry 4.0, skills in data analysis are becoming increasingly important, and education must adapt to meet this need. Currently, there are still many students at the vocational high school level who do not understand the concept of data science, including clustering techniques, so they have difficulty understanding how data can be generated for decision making from each scheme. The method that can be used in this Community Service is an introduction to the basic concepts of data science and simple training in the use of simple data science tools. The goal that can be raised for the Community Service that we do is to provide students with a basic understanding of what data science is as one method for making important data decisions. The contribution that can be generated from the Community Service that we do is that students will have basic skills in knowledge related to data science, especially in understanding and applying clustering techniques for data analysis. The result of the Community Service that we do is that students understand the basic concepts of data science and clustering and how this method is applied in the analysis of the data obtained.
IMPLEMENTASI PEMBLOKAN SITUS DENGAN FIREWALL LAYER 7 PROTOCOL MENGGUNAKAN METODE NDLC PADA ROUTER MIKROTIK Imawan, Sonny Aditya; Dwiasnati, Saruni
MULTINETICS Vol. 11 No. 1 (2025): Vol. 11 No. 1 (2025): MULTINETICS Mei (2025)
Publisher : POLITEKNIK NEGERI JAKARTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32722/multinetics.v11i1.6844

Abstract

In the current era of technological advancement, companies' dependency on computer networks is increasing. Intensive internet usage during working hours presents challenges in efficiently managing bandwidth. Uncontrolled activities such as accessing social media, playing online games, and streaming videos can degrade network quality, disrupt productivity, and cause service dissatisfaction. This research aims to enhance the efficiency of network usage in the company by focusing on reducing bandwidth due to uncontrolled internet usage, particularly by identifying and blocking access to websites unrelated to work activities using Firewall Layer 7 Protocol. Approximately 45% of employees frequently visit other sites during working hours. System development is carried out using the Network Development Life Cycle (NDLC) method, which illustrates the continuous cycle of computer network development. Testing results in the research using the BlackBox method with Winbox software to assess the planned system performance successfully blocked sites, online games, and increased bandwidth; after implementation, the bandwidth achieved was above 50Mbps during working hours. This method is expected to provide effective solutions to improve network quality, optimize bandwidth usage, and support overall company productivity.
Rancangan Sistem Dalam Pengelolaan Data Penduduk Pada Kantor Desa Boloak Menggunakan Algoritma Sequential Searching Qitala, Shofia; Dwiasnati, Saruni
CSRID (Computer Science Research and Its Development Journal) Vol. 15 No. 3 (2023): October 2023
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.15.3.2023.189-199

Abstract

Fast and accurate information will support the smooth operation or management of the village government, in managing community data and information. Currently, various administrations and data management at the Boloak village office are still being carried out manually, and have not been computerized so that the performance in managing population data is still not optimal. For this reason, in utilizing information technology for managing population data and assistance data, an information system design is needed for the scope of the alternating village office, so that it can support smooth operations and improve performance for village government employees. With the aim of this research being to design a population data management system and assistance data by implementing a web-based Sequential Searching Algorithm using php and using the MySql database, this research will be designed using the waterfall method, making it easier for employees to search population data, identify population data as well as in managing social assistance data more efficiently and improving the performance of village officials in managing data.
Pengelompokan wilayah produksi tuna, cakalang, tongkol dan udang di Indonesia menggunakan algoritma K-Means Dwiasnati, Saruni; eliyani, Eliyani; Arif, Sutan Mohammad; Avrizal, Reza
IT Explore: Jurnal Penerapan Teknologi Informasi dan Komunikasi Vol 4 No 2 (2025): IT-Explore Juni 2025
Publisher : Fakultas Teknologi Informasi, Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24246/itexplore.v4i2.2025.pp128-137

Abstract

The research was intended to cluster the production areas of Indonesia's fishery products especially Skipjack Tuna, Tuna, Mackarel Tuna, and shrimp using data science techniques. The algorithm used was K-means Clustering. The data used was annual production data for each province for the last 3 years (2019 – 2021). Determination of the number of clusters using the Elbow Method. For each commodity, three clusters were obtained, namely clusters with low production, medium production, and high production. For Skipjack Tuna, there were 19 provinces belonging to the low cluster, 13 provinces being medium, and 2 provinces being high. For Tuna, there were 22 provinces in the low cluster, 9 provinces in the middle, and 3 provinces in the high cluster. For Mackarel Tuna, low was 19 provinces, medium was 12 provinces, and high was 3 provinces. For shrimp, 23 provinces were low, 7 provinces were medium, and 4 provinces were high. High production clusters for Skipjack Tuna were North Sulawesi and North Maluku Provinces, Tuna were North Sulawesi, North Maluku and Maluku Provinces, for Mackarel Tuna were Aceh, East Java and Maluku Provinces, and for shrimp were North Sumatra, West Kalimantan, South Kalimantan and East Kalimantan Provinces.
Application of Machine Learning in Clustering Maize Producing Regions in Indonesia Eliyani; Dwiasnati, Saruni; Arif , Sutan Mohammad; Avrizal, Reza; Fatimah, Nona
Computer Engineering and Applications Journal (ComEngApp) Vol. 13 No. 2 (2024)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Maize is considered an important commodity with promising market prospects. Given the importance of maize, there is a need to increase maize production to meet people's needs and maintain price stability. This study aims to group maize production in Indonesia by region, with the hope of finding areas that have the potential to become maize production centers to reduce dependence on imports. The data used in this research was obtained from the Central Statistics Agency, covering information from 34 provinces during the 2017-2021 period. This analysis uses the K-Means method with the Python programming language. The number of groups is determined using the Elbow Method. The results of this research show that there are three categories of maize production regions: regions with low maize production (below average), regions with medium maize production, and regions with high maize production. A total of 25 provinces are in the low production category, eight provinces are in the medium category, and only East Java is in the high production category.
Comparison of Naive Bayes and Support Vector Machine (SVM) Algorithms Regarding The Popularity of Presidential Candidates In The Upcoming 2024 Presidential Election Nurrizky, Fadli; Dwiasnati, Saruni
Computer Engineering and Applications Journal (ComEngApp) Vol. 13 No. 1 (2024)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study aims to compare the effectiveness of two classification algorithms, Naive Bayes and Support Vector Machine (SVM), in analyzing the popularity of presidential candidates for the 2024 Presidential Election (Pilpres). The popularity of presidential candidates plays a crucial role in campaign strategies and political decision-making in the modern political era. This research utilizes data from social media, encompassing public sentiment towards presidential candidates and related political issues. The research results indicate that SVM achieves an accuracy rate of 97%, while Naive Bayes achieves 95%, demonstrating the superiority of SVM in predicting the popularity of presidential candidates. In conclusion, the selection of the appropriate algorithm for analyzing complex political data has a significant impact, and the high accuracy rates of both algorithms provide valuable guidance for political decisionmakers and campaign teams in preparation for the upcoming 2024 Pilpres.
Pelatihan Klasifikasi Data Menggunakan Naive Bayes untuk Mengembangkan Literasi Data di SMK Media Informatika Dwiasnati, Saruni; Devianto, Yudo; Yuliarty, Popy; Gunawan, Wawan
IRA Jurnal Pengabdian Kepada Masyarakat (IRAJPKM) Vol 3 No 1 (2025): April
Publisher : CV. IRA PUBLISHING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56862/irajpkm.v3i1.166

Abstract

Data processing skills are essential in the digital era, especially for vocational high school (SMK) students preparing for technology-driven careers. This community service activity aimed to enhance data literacy among SMK Media Informatika students through training in data classification using the Naive Bayes algorithm, a fundamental method in data science and machine learning. The algorithm was chosen for its simplicity, ease of understanding, and relevance in introducing probabilistic decision-making logic. The training was conducted interactively, covering basic data concepts, dataset visualization, and practical implementation using Python. The results showed improved student understanding of classification concepts and their application to real-world problems, such as user data category prediction. The activity also encouraged analytical thinking, awareness of valid data collection, and interest in data science. This training is expected to serve as a model for applied learning in vocational schools and support the development of data-oriented curricula at the vocational education level.