IRPI Publisher Journals (Institute of Research and Publication Indonesia)
Not a member yet
1012 research outputs found
Sort by
Evaluation of the Effectiveness of Neural Network Models for Analyzing Customer Review Sentiments on Marketplace
Get PDFAccording to the 2019 report, Tokopedia is the most visited marketplace with 140,000,000 visitors per month, making it one of the most popular marketplaces in Indonesia. Customers have the opportunity to write reviews about the products they purchase at the end of the transaction process on Tokopedia. The aim of this research is to conduct sentiment analysis on product reviews on Tokopedia. Three neural networks that will be used for text classification are Bi-GRU, GRU, and LSTM. The data processing technique is divided into training and testing samples, split into 80%:20% using the holdout technique. The BI-GRU algorithm has an accuracy of 0.93% and precision of 0.96, better than the other two methods LSTM and GRU, which each have an accuracy of 0.92 and recall of 0.91
Comparison of TOPSIS and SMARTER Methods in Selecting Delivery Services
Get PDFThe rapid growth of the e-commerce world has propelled the demand for freight forwarding services, a pivotal component in maintaining the smooth flow of this business. Major companies like JNE, TIKI, Kantor Pos Indonesia, SiCepat, and J&T Express are involved. However, despite this convenience, various challenges often accompany the shipping process. Some of these include delayed deliveries, lost or damaged items, or even misdeliveries to the wrong customers. This presents a dilemma for leading e-commerce companies in selecting the most suitable delivery service partner. Hence, a decision support model is necessary in choosing a freight forwarding service. This study will outline comparison methods based on both Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) and Simple Multi Attribute Rating Technique Exploiting Ranks (SMARTER). The proposed methods have strong relevance to the rapid growth of the e-commerce world. This research emphasizes the importance of selecting freight forwarding services in maintaining the smooth operation of e-commerce businesses. The results of this study have obtained ranking results from the final value of each method. The first place in the TOPSIS method with a value of 0.7033 at sensitivity 3 and the lowest in the SMARTER method with a value of 0.1303 at the first sensitivity, and at the second sensitivity, all methods have the same value of 0.2. The conclusion is that TOPSIS is the best method compared to the SMARTER method as a decision support for the selection of freight forwarding services
Comparison of Machine Learning Algorithms in Diabetes Risk Classification
Get PDFDiabetes is a disease in which blood sugar levels are excessive without insulin control so that body functions do not function normally. Diabetes is also a disease that many people suffer from and is one of the main causes of death throughout the world. For this reason, we need to know the factors that are indicators of someone suffering from diabetes. This research compares the Decision Tree, Logistic Regression, and K-Nearest Neighbors algorithms with accuracy and Confusion Matrix parameters to determine diabetes sufferers in 520 data with the main indicator attributes supporting diabetes. From the test results of the three algorithms, the Decision Tree and K-Nearest Neighbors models have the highest accuracy of 86%. The Logistic Regression Algorithm has a fairly good accuracy of 83%
Prediksi Risiko Stunting pada Keluarga Menggunakan Naïve Bayes Classifier dan Chi-Square: Prediction of Stunting Risk In Families Using Naïve Bayes Classifier and Chi-Square
No full textStunting merupakan sesuatu yang berbahaya pada manusia karena dapat menyebabkan terjadinya hambatan pertumbuhan serta perkembangan organ lainnya termasuk otak, jantung dan ginjal. Meningkatnya kasus stunting pada balita memerlukan suatu upaya dalam penanganan dan pencegahan secara dini. Terdapat 17 atribut pada data stunting yang harus diperhatikan, dengan banyaknya atribut tersebut menyebabkan sulitnya menemukan atribut yang paling berpengaruh dalam memprediksi stunting. Pada penelitian ini diterapkan seleksi fitur menggunakan Chi Square dan menerapkan Algoritma Naïve Bayes untuk menemukan atribut yang harus diprioritaskan dalam memprediksi stunting. Hasil prediksi dengan menggunakan Naive bayes saja pada penelitian ini didapatkan nilai akurasi sebesar 94,3 %, nilai recall sebesar 93,9 % dan nilai precision sebesar 93,93% dengan waktu 0,07 detik. Sedangkan dengan menerapkan seleksi fitur Chi square pada penelitian ini diperoleh 5 atribut yang paling berpengaruh terhadap prediksi stunting yang dapat meningkatkan kecepatan pembentukkan model Algoritma Naiva Bayes dengan waktu 0,01 detik, namun tidak dapat meningkatkan akurasi, recall dan presisi. Harapannya instansi terkait dapat lebih memperhatikan dan memprioritaskan ke-5 atribut tersebut sebagai pemantauan prediksi stunting di Kota Dumai
Fuzzy Clustering-Based Grouping for Mapping the Distribution of Student Success Data
Get PDFLearning activities are the main activity in the overall teaching and learning process in schools. This is because whether or not the achievement of educational goals depends on how the learning process is carried out by students. The uneven level of student success in learning is one of the problems in the school's efforts to realize the vision and mission of SMKN 5 Pekanbaru in preparing skilled graduates to be able to work in certain sectors by the public interest and the industrial world. In this study, mapping and grouping student grade data was carried out using the Fuzzy C-Means algorithm to provide information to the school in making the right decisions and optimizing the learning process. Furthermore, clustering was carried out in several experiments K=3 to K=7, and obtained the best validity value tested with the Silhouette Index of 0.4277 located at K=5. Then the distribution of cluster 5 on student score data was obtained with details, namely cluster 1 with a capacity of 1 student, cluster 2 with a capacity of 27 students, cluster 3 with a capacity of 1 student, cluster 4 with a capacity of 10 students, cluster 5 with a capacity of 23 students
Information Security Management System Assessment Model by Integrating ISO 27002 and 27004
Get PDFThe rapid development of information and communication technology has also led to a significant increase in cybercrime activities. According to the Annual Cybersecurity Monitoring Report by the National Cyber and Cryptography Agency, there were 495 million instances of traffic anomalies or attempted attacks in 2020, which rose to 1.6 billion in 2021 in Indonesia. Implementing the ISO 27001 standard for information security management system (ISMS) can help mitigate these cyber-attack attempts. However, with various levels of resources and organizational commitment, different levels of ISMS maturity can be achieved. Therefore, there is a need for an ISMS assessment model. This is crucial, considering cyber incidents such as data breaches in organizations that have implemented or are certified with ISO 27001. This research proposed a concept of ISMS assessment model by integrating ISO 27002 and 27004 to a case study (Directorate XYZ), where the guidance function of ISO 27002 is transformed into assessment parameters and ISO 27004 for measuring performance. Using this model, the score of the case study’s ISMS was found to be 53.925, which is still below the established standard of 80
Perancangan Infrastruktur Jaringan Komputer dengan Media Transmisi Wired dan Nirkabel Menggunakan Cisco Packet Tracer: Design of Computer Network Infrastructure with Wired and Wireless Transmission Media Using Cisco Packet Tracer
No full textTeknologi jaringan komputer merupakan komponen penting dalam mendukung aktivitas belajar mengajar di lingkungan Pendidikan. Penggunaan teknologi dalam bidang pendidikan membantu proses belajar dan meningkatkan kinerja dengan membuat, menggunakan, dan mengelola proses dan sumber teknologi yang memadai. Penelitian ini berfokus pada perancangan serta menkonfigurasi infrastruktur jaringan komputer di SDN Jati 06 Jakarta Timur, dengan menggabungkan media transmisi wired dan nirkabel untuk meningkatkan efisiensi dan keandalan jaringan. Metodologi yang digunakan melibatkan simulasi menggunakan Cisco Packet Tracer untuk merancang topologi jaringan serta men konfigurasi perangkat. Hasil yang dicapai yaitu bagaimana rancangan infrastruktur jaringan komputer internet dengan media wired dan nirkabel ini memiliki manajemen jaringan yang baik, pengalamat IP address yang baik, serta dapat mengestimasi alat apa saja yang diperlukan. Kesimpulan dari penelitian ini menyarankan bahwa desain jaringan hybrid ini sangat sesuai untuk memenuhi kebutuhan komunikasi data di lingkungan pendidikan, memberikan solusi yang scalable dan adaptif terhadap perkembangan teknologi khusus nya di SDN Jati 06 Jakarta Timur
Simulasi Pemilu untuk Pemilih Pemula Berbasis Mixed Reality: Election Simulation for Beginner Voters Based on Mixed Reality
No full textPemilihan umum (pemilu) merupakan salah satu pilar utama dalam sistem demokrasi di Indonesia yang memiliki fungsi sebagai alat untuk melakukan pemilihan yang akan menjadi pemimpin. Partisipasi pemilu pada pemilih pemula menunjukkan angka penurunan, dikarenakan pemilih pemula merasa kesulitan dalam teknis untuk mengikuti pemilihan umum. Maka dari itu, membuat suatu simulasi pemilu yang menggunakan teknologiMixed Reality (MR) yaitu memadukan antara Virtual Reality (AR) dan Augmented Reality (AR). Tujuan dari menggunakan teknologi mixed reality, dapat memberi pengalaman langsung bagi pemilih pemula dalam melaksanakan teknis pemilu. Selain itu meningkatkan antusias pemilih pemula dalam pemilu melalui teknologi. Penelitian ini dilaksanakan menggunakan metode kualitatif, dengan wawancara mendalam dan observasi sebagai teknik pengumpulan data. Partisipan dalam penelitian ini merupakan siswa menengah atas kelas 11 dan 12.Simulasi yang akan kembangkan nantinya dapat dijalankan dengan perangkat keras Virtual Reality, kemudian dengan perangkat keras tersebut sensor akan mendeteksi tangan dan area yang akan kita gunakan untuk menampilkan objek 3D, sehingga kita bisamelakukan simulasi pemilu dengan pengalaman lebih interaktif dan menarik bagi pemilih pemula. Hasil penelitian ini menunjukan bahwa para pemilih pemula lebih terbantu untuk memahami teknis pemilu dengan perpaduan teknologi. Agar nantinya angka partisipasi pemilih pemula mengalami kenaikan dan para pemula memiliki pemahaman teknis yang cukup terhadap pemilu
Design and Analysis of Cybersecurity Information Sharing Mechanism Between Computer Security Incident Response Teams (CSIRT) in Indonesia on Blockchain Technology Through Hyperledger Composer and Interplanetary File System (IPFS)
Get PDFSharing cybersecurity information among the Computer Security Incident Response Team (CSIRT) is a crucial step in enhancing organizational cybersecurity. However, a primary challenge faced is the lack of trust among users regarding the confidentiality, integrity, and availability of shared information. This study proposes a new approach by designing a mechanism for sharing cybersecurity information among CSIRTs in Indonesia on blockchain technology using Hyperledger Composer. This approach offers an innovative solution by leveraging the advantages of blockchain technology. Through this approach, cybersecurity information can be shared in a decentralized manner, overcoming the weaknesses of centralized systems, and enhancing overall information security. Another advantage of blockchain technology is its high performance and scalability, enabling increased speed, and user capacity in the process of sharing information. By implementing a blockchain-based mechanism for sharing cybersecurity information, this research aims to ensure crucial aspects of information security, namely confidentiality, integrity, and availability. The contribution of this study is not only in enhancing organizational cybersecurity but also in providing an innovative solution to practical challenges in sharing cybersecurity information among CSIRTs
Peramalan Ekspor Batu Bara Indonesia Menggunakan Metode Double Exponential Smoothing Brown: Forecasting Indonesian Coal Exports Using Double Exponential Smoothing Brown Method
No full textBatu bara adalah sumber energi penting untuk pembangkit listrik di banyak negara. Sebagai sumber daya alam yang tidak dapat diperbaharui, batu bara tersedia di berbagai negara termasuk Indonesia. Indonesia memiliki sumber daya batu bara sekitar 161 miliar ton dengan cadangan mencapai 28 miliar ton. Indonesia merupakan negara pengekspor batu bara terbesar di dunia dan produsen kedua terbesar. Sekitar 75% dari produksi batu bara di Indonesia diekspor ke luar negeri, sementara 25% digunakan untuk keperluan domestik. Berdasarkan potensi sumber daya batu bara yang besar dan dominasi ekspor yang signifikan dibandingkan dengan konsumsi dalam negeri, peramalan ekspor batu bara di Indonesia menjadi sangat penting. Peramalan ini memberikan panduan untuk mengoptimalkan produksi batu bara dengan tujuan memaksimalkan keuntungan negara tanpa mengorbankan kelestarian lingkungan. Dengan demikian, beberapa kebijakan dapat dipilih berdasarkan pendekatan strategis yang diambil untuk menjaga keseimbangan antara manfaat ekonomi dan keberlanjutan lingkungan. Terdapat beberapa pendekatan untuk memprediksi ekspor batu bara di Indonesia, termasuk menggunakan metode Double Exponential Smoothing Brown. Hasil peramalan tren produksi batu bara Indonesia untuk periode 2023-2027 adalah sebanyak 354.847,71 ribu ton, 353.656,62 ribu ton, 352.465,52 ribu ton, 351.274,43 ribu ton, dan 350.083,33 ribu ton. Penelitian ini menunjukkan bahwa nilai Minimum Absolute Percentage Error (MAPE) terendah yang dicapai adalah 0,06212