CV. XYZ is a company engaged in selling fabrics. The company's current customers are around 372 customers, of which 81% or around 301 customers only make transactions less than 10 times and 19% or around 71 customers make transactions more than 10 times, this shows a low level of customer loyalty towards the company. Company owners currently have difficulty determining the type of promotion that will be given to each customer based on their level of loyalty. The method used to segment customers is the Recency, Frequency and Monetary (RFM) method and delivering promotions to customers using WhatsApp API Gateway Services. The results of this RFM method can make it easier for company owners to determine the type of promotion that will be given to each customer as well as the delivery of the promotion in an effort to increase customer loyalty to the company. Of the 24 customers used as sample data, the Most Valuable Customer group has 4 customers, the Most Growable Customer group has 15 customers, the Migrator group has 5 customers and the Below Zeros group has 0 customers.
{"title":"Sistem Penentuan Jenis Promosi Berdasarkan Tingkat Loyalitas Pelanggan di CV. XYZ","authors":"Riani Lubis, Tati Harihayati Mardzuki, Aditya Akhmad Gufron","doi":"10.34010/komputa.v12i2.9405","DOIUrl":"https://doi.org/10.34010/komputa.v12i2.9405","url":null,"abstract":"CV. XYZ is a company engaged in selling fabrics. The company's current customers are around 372 customers, of which 81% or around 301 customers only make transactions less than 10 times and 19% or around 71 customers make transactions more than 10 times, this shows a low level of customer loyalty towards the company. Company owners currently have difficulty determining the type of promotion that will be given to each customer based on their level of loyalty. The method used to segment customers is the Recency, Frequency and Monetary (RFM) method and delivering promotions to customers using WhatsApp API Gateway Services. The results of this RFM method can make it easier for company owners to determine the type of promotion that will be given to each customer as well as the delivery of the promotion in an effort to increase customer loyalty to the company. Of the 24 customers used as sample data, the Most Valuable Customer group has 4 customers, the Most Growable Customer group has 15 customers, the Migrator group has 5 customers and the Below Zeros group has 0 customers.","PeriodicalId":477061,"journal":{"name":"Komputa: Jurnal Ilmiah Komputer dan Informatika","volume":"36 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135775655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Vehicles are a means of transportation that have existed from ancient times until now, many people use vehicles such as cars and motorbikes. Enumeration of types and numbers of vehicles is carried out to collect traffic data information. In obtaining data parameters for the number of vehicles, manual calculations are usually prone to errors and take a lot of time and energy. The application of Artificial Intelligence such as object detection is a field of computer vision. In intelligent transportation systems, traffic data is the key to conducting research and designing a system. To overcome the problem, researchers carried out object tracking using the You Only Look Once (YOLO) v8 algorithm to detect the type and count the number of vehicles. The methodology applied is the AI Project Cycle stages which use problem scoping, data acquisition, data exploration, modeling, and confusion matrix evaluation. The results of the confusion matrix evaluation obtained an accuracy level of 89%, precision of 89%, recall of 90% and a weighted comparison of precision and recall obtained an F1-Score value of 89%. Thus, the You Only Look Once (YOLO) v8 algorithm is accurate enough to detect object tracking to calculate vehicles.
车辆是一种从古至今一直存在的交通工具，许多人使用汽车和摩托车等交通工具。通过列举车辆种类和数量来收集交通数据信息。在获取车辆数量的数据参数时，人工计算往往容易出错，耗费大量的时间和精力。物体检测等人工智能的应用是计算机视觉的一个领域。在智能交通系统中，交通数据是进行系统研究和设计的关键。为了克服这个问题，研究人员使用You Only Look Once (YOLO) v8算法进行了目标跟踪，以检测车辆的类型并计算车辆的数量。应用的方法是人工智能项目周期阶段，使用问题范围界定、数据采集、数据探索、建模和混淆矩阵评估。混淆矩阵评价结果的准确率为89%，准确率为89%，召回率为90%，准确率和召回率加权比较的F1-Score值为89%。因此，You Only Look Once (YOLO) v8算法足够精确，可以检测物体跟踪以计算车辆。
{"title":"Object Tracking Menggunakan Algoritma You Only Look Once (YOLO)v8 untuk Menghitung Kendaraan","authors":"Nurhaliza Juliyani Hayati, Dayan Singasatia, Muhamad Rafi Muttaqin","doi":"10.34010/komputa.v12i2.10654","DOIUrl":"https://doi.org/10.34010/komputa.v12i2.10654","url":null,"abstract":"Vehicles are a means of transportation that have existed from ancient times until now, many people use vehicles such as cars and motorbikes. Enumeration of types and numbers of vehicles is carried out to collect traffic data information. In obtaining data parameters for the number of vehicles, manual calculations are usually prone to errors and take a lot of time and energy. The application of Artificial Intelligence such as object detection is a field of computer vision. In intelligent transportation systems, traffic data is the key to conducting research and designing a system. To overcome the problem, researchers carried out object tracking using the You Only Look Once (YOLO) v8 algorithm to detect the type and count the number of vehicles. The methodology applied is the AI Project Cycle stages which use problem scoping, data acquisition, data exploration, modeling, and confusion matrix evaluation. The results of the confusion matrix evaluation obtained an accuracy level of 89%, precision of 89%, recall of 90% and a weighted comparison of precision and recall obtained an F1-Score value of 89%. Thus, the You Only Look Once (YOLO) v8 algorithm is accurate enough to detect object tracking to calculate vehicles.","PeriodicalId":477061,"journal":{"name":"Komputa: Jurnal Ilmiah Komputer dan Informatika","volume":"36 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135775826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Steganography is a method for concealing sensitive information in seemingly unremarkable data. In recent years, the use of steganography in web applications has become popular due to its accessibility and ability to conceal data in various types of media. Implementing a web-based steganography program that makes use of the Bit-Plane Complexity and Least Significant Bit algorithms is the aim of this project. To enable users to access the application through a browser, the system is constructed utilizing web technologies like HTML, CSS, and JavaScript during the design phase. The LSB and BPCS algorithms are employed as methods to embed secret data into user-selected images. The least significant bit of each image pixel is utilized to hold a secret piece of information using the straightforward steganography technique known as LSB. On the other hand, BPCS is a more complex steganography method that combines spatial and frequency domain analysis to hide data within high-quality images. The findings of this study show that the technique of hiding sensitive information within photos is successfully implemented by the web-based steganography program employing the LSB and BPCS algorithms.
{"title":"Implementasi Aplikasi Steganografi Berbasis Web Menggunakan Algoritma LSB dan BPCS","authors":"Laily Farkhah Adhimah, Isti Nurhafiyah, Adnan Aditya Muntahar, Fandi Kristiaji, Dinar Mustofa","doi":"10.34010/komputa.v12i2.10319","DOIUrl":"https://doi.org/10.34010/komputa.v12i2.10319","url":null,"abstract":"Steganography is a method for concealing sensitive information in seemingly unremarkable data. In recent years, the use of steganography in web applications has become popular due to its accessibility and ability to conceal data in various types of media. Implementing a web-based steganography program that makes use of the Bit-Plane Complexity and Least Significant Bit algorithms is the aim of this project. To enable users to access the application through a browser, the system is constructed utilizing web technologies like HTML, CSS, and JavaScript during the design phase. The LSB and BPCS algorithms are employed as methods to embed secret data into user-selected images. The least significant bit of each image pixel is utilized to hold a secret piece of information using the straightforward steganography technique known as LSB. On the other hand, BPCS is a more complex steganography method that combines spatial and frequency domain analysis to hide data within high-quality images. The findings of this study show that the technique of hiding sensitive information within photos is successfully implemented by the web-based steganography program employing the LSB and BPCS algorithms.","PeriodicalId":477061,"journal":{"name":"Komputa: Jurnal Ilmiah Komputer dan Informatika","volume":"36 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135775653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-04DOI: 10.34010/komputa.v12i2.10997
Louis Maximillian, Yosefina Finsensia Riti, Mario Anugraha Agung, Yohanes Junardi Palis
Penyakit daun yang umum terjadi pada tanaman lidah buaya, seperti busuk daun, busuk akar, infeksi bakteri, dan serangan virus, dapat menimbulkan kerusakan yang cukup parah. Identifikasi penyakit-penyakit tersebut masih mengandalkan pengalaman petani dan seringkali menimbulkan interpretasi yang salah. Solusi modern telah ditemukan melalui penerapan teknologi informasi, khususnya di bidang pengolahan citra digital. Dengan menggunakan metode ini, diagnosis penyakit pada daun lidah buaya dapat ditingkatkan melalui deteksi tepi objek pada gambar daun. Hasil deteksi tepi ini memungkinkan mengidentifikasi gejala penyakit dengan lebih akurat. Dalam konteks ini, algoritma Canny dan Sobel, dua algoritma yang umum digunakan untuk deteksi tepi pada gambar, terbukti menjadi pilihan yang efektif. Dengan menggunakan metode tersebut, gambar tepi daun lidah buaya dapat diidentifikasi secara akurat. Ini adalah langkah penting dalam mendukung petani dalam diagnosis dini penyakit dan mengambil tindakan tepat waktu untuk mengatasi masalah ini. Penelitian ini bertujuan untuk mendapatkan algoritma terbaik pendeteksian tepi daun lidah buaya berdasarkan nilai Mean Squared Error (MSE) dan Peak Signal-to-Noise Ratio (PSNR). Hasil pengujian menunjukkan bahwa algoritma Sobel memberikan hasil yang lebih baik dengan rata-rata pengukuran MSE sebesar 2781.88 dan rata-rata PSNR sebesar 14.04, sedangkan algoritma Canny memiliki rata-rata MSE sebesar 3542.02 dan rata-rata PSNR sebesar 12.92.
{"title":"Perbandingan Algoritma Sobel dan Canny untuk Deteksi Tepi Citra Daun Lidah Buaya","authors":"Louis Maximillian, Yosefina Finsensia Riti, Mario Anugraha Agung, Yohanes Junardi Palis","doi":"10.34010/komputa.v12i2.10997","DOIUrl":"https://doi.org/10.34010/komputa.v12i2.10997","url":null,"abstract":"Penyakit daun yang umum terjadi pada tanaman lidah buaya, seperti busuk daun, busuk akar, infeksi bakteri, dan serangan virus, dapat menimbulkan kerusakan yang cukup parah. Identifikasi penyakit-penyakit tersebut masih mengandalkan pengalaman petani dan seringkali menimbulkan interpretasi yang salah. Solusi modern telah ditemukan melalui penerapan teknologi informasi, khususnya di bidang pengolahan citra digital. Dengan menggunakan metode ini, diagnosis penyakit pada daun lidah buaya dapat ditingkatkan melalui deteksi tepi objek pada gambar daun. Hasil deteksi tepi ini memungkinkan mengidentifikasi gejala penyakit dengan lebih akurat. Dalam konteks ini, algoritma Canny dan Sobel, dua algoritma yang umum digunakan untuk deteksi tepi pada gambar, terbukti menjadi pilihan yang efektif. Dengan menggunakan metode tersebut, gambar tepi daun lidah buaya dapat diidentifikasi secara akurat. Ini adalah langkah penting dalam mendukung petani dalam diagnosis dini penyakit dan mengambil tindakan tepat waktu untuk mengatasi masalah ini. Penelitian ini bertujuan untuk mendapatkan algoritma terbaik pendeteksian tepi daun lidah buaya berdasarkan nilai Mean Squared Error (MSE) dan Peak Signal-to-Noise Ratio (PSNR). Hasil pengujian menunjukkan bahwa algoritma Sobel memberikan hasil yang lebih baik dengan rata-rata pengukuran MSE sebesar 2781.88 dan rata-rata PSNR sebesar 14.04, sedangkan algoritma Canny memiliki rata-rata MSE sebesar 3542.02 dan rata-rata PSNR sebesar 12.92.","PeriodicalId":477061,"journal":{"name":"Komputa: Jurnal Ilmiah Komputer dan Informatika","volume":"36 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135775654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-09DOI: 10.34010/komputa.v12i2.10506
Arief Rachman Hakim, Wiga Maulana Baihaqi
Indonesia is the largest archipelagic country in the world which has very strategic geography. This can bring many opportunities in exploring natural riches and environmental services. For this reason, the existence of reliable and efficient transportation is very important. One means of transportation that is very popular and widely used by the public is airplanes. In this case, aircraft have made a significant contribution in supporting global connectivity, tourism and economic growth in various sectors. Even though airplane transportation has various advantages, there are still shortcomings in the airplane ticket purchasing process which still relies heavily on travel agents or direct purchases through the destination airline. This often causes problems, such as unstable ticket prices and concerns regarding the security of the ticket purchasing process. One innovation that can be a solution to the problem of purchasing plane tickets is the development of an application that provides a platform for purchasing plane tickets from various airlines. This application will combine various ticket options from various airlines on one platform. Apart from that, the application will also ensure the safety and security of passengers by providing the latest information about the availability of facilities on the plane and payment methods that are familiar to users. Thus, this application will provide convenience, comfort and security for prospective passengers in purchasing airline tickets of their choice.
{"title":"RANCANG BANGUN SISTEM PEMESANAN TIKET PESAWAT BERBASIS WEB","authors":"Arief Rachman Hakim, Wiga Maulana Baihaqi","doi":"10.34010/komputa.v12i2.10506","DOIUrl":"https://doi.org/10.34010/komputa.v12i2.10506","url":null,"abstract":"Indonesia is the largest archipelagic country in the world which has very strategic geography. This can bring many opportunities in exploring natural riches and environmental services. For this reason, the existence of reliable and efficient transportation is very important. One means of transportation that is very popular and widely used by the public is airplanes. In this case, aircraft have made a significant contribution in supporting global connectivity, tourism and economic growth in various sectors. Even though airplane transportation has various advantages, there are still shortcomings in the airplane ticket purchasing process which still relies heavily on travel agents or direct purchases through the destination airline. This often causes problems, such as unstable ticket prices and concerns regarding the security of the ticket purchasing process. One innovation that can be a solution to the problem of purchasing plane tickets is the development of an application that provides a platform for purchasing plane tickets from various airlines. This application will combine various ticket options from various airlines on one platform. Apart from that, the application will also ensure the safety and security of passengers by providing the latest information about the availability of facilities on the plane and payment methods that are familiar to users. Thus, this application will provide convenience, comfort and security for prospective passengers in purchasing airline tickets of their choice.","PeriodicalId":477061,"journal":{"name":"Komputa: Jurnal Ilmiah Komputer dan Informatika","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135197110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-09DOI: 10.34010/komputa.v12i2.10904
Anton - Anton, Naufal Naufal
The sales of pajama products on i_docraft have not yet leveraged data mining algorithms to analyze transactional data for optimizing sales. To avoid underperforming pajama models and determine which pajama models sell well, the utilization of the Apriori algorithm is necessary. The Apriori algorithm can discern these patterns based on transactional data. This study conducts a transactional data analysis using data mining with the Apriori algorithm. By employing this algorithm, the most frequently sold pajama products can be identified, allowing for prioritization of these models and the development of marketing strategies for other types of pajamas based on a comparison of their strengths and commonly high sales figures. The processed data yields associations rules for concurrently sold pajama items. Based on the results of the final association rules meeting both predetermined minimum support and confidence criteria, for instance, if a product with item code 7 (Cherrypie Nightdress) is purchased, then a product with item code 17 (3 in 1 Lotso Set) will likely be bought with a support value of 22.58% and a confidence value of 100%.
i_docraft上睡衣产品的销售还没有利用数据挖掘算法来分析交易数据以优化销售。为了避免表现不佳的睡衣模型，确定哪些睡衣模型卖得好，有必要使用Apriori算法。Apriori算法可以根据事务数据识别这些模式。本研究使用Apriori算法的数据挖掘进行事务性数据分析。通过使用这种算法，可以识别出最常销售的睡衣产品，允许对这些模型进行优先排序，并根据它们的优势和通常较高的销售数据的比较，为其他类型的睡衣制定营销策略。处理后的数据产生并发销售的睡衣商品的关联规则。根据最终关联规则的结果，同时满足预定的最小支持度和置信度标准，例如，如果购买商品代码为7的产品(Cherrypie Nightdress)，则可能购买商品代码为17的产品(3 in 1 Lotso Set)，其支持值为22.58%，置信度为100%。
{"title":"IMPLEMENTASI ALGORITMA APRIORI UNTUK MENENTUKAN PRODUK TERLARIS PADA TOKO I_DOCRAFT","authors":"Anton - Anton, Naufal Naufal","doi":"10.34010/komputa.v12i2.10904","DOIUrl":"https://doi.org/10.34010/komputa.v12i2.10904","url":null,"abstract":"The sales of pajama products on i_docraft have not yet leveraged data mining algorithms to analyze transactional data for optimizing sales. To avoid underperforming pajama models and determine which pajama models sell well, the utilization of the Apriori algorithm is necessary. The Apriori algorithm can discern these patterns based on transactional data. This study conducts a transactional data analysis using data mining with the Apriori algorithm. By employing this algorithm, the most frequently sold pajama products can be identified, allowing for prioritization of these models and the development of marketing strategies for other types of pajamas based on a comparison of their strengths and commonly high sales figures. The processed data yields associations rules for concurrently sold pajama items. Based on the results of the final association rules meeting both predetermined minimum support and confidence criteria, for instance, if a product with item code 7 (Cherrypie Nightdress) is purchased, then a product with item code 17 (3 in 1 Lotso Set) will likely be bought with a support value of 22.58% and a confidence value of 100%.","PeriodicalId":477061,"journal":{"name":"Komputa: Jurnal Ilmiah Komputer dan Informatika","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135197109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-07DOI: 10.34010/komputa.v12i2.10157
Nila Nazilatul Mazaya, Suliswaningsih Suliswaningsih
Changes in people's lifestyles are caused by the ease of use of technology, especially in the entertainment sector. In the field of entertainment, music is certainly no stranger to society, from children to parents. With digital advances and internet technology, music can be heard by millions of music lovers from all over the world. Music applications can increase interest and attract user attention to continue using them or diminish because they are bored using them. Problems that often occur when listening to music include not being user friendly, prices are quite expensive especially for students or students and also the services provided are less attractive. This study aims to find out how to increase user interest and keep it interesting using a music application. Therefore, the author tries to design a music application, namely the Dengerin Application. This design uses the Design Thinking method because it can produce creative solutions. In testing using a usability testing system with a score of 77,5. The result of this research is the design of mobile-based “Dengerin” application interface ehich was designed using figma.
{"title":"PERANCANGAN UI/UX APLIKASI “DENGERIN” BERBASIS MOBILE MENGGUNAKAN METODE DESIGN THINKING","authors":"Nila Nazilatul Mazaya, Suliswaningsih Suliswaningsih","doi":"10.34010/komputa.v12i2.10157","DOIUrl":"https://doi.org/10.34010/komputa.v12i2.10157","url":null,"abstract":"Changes in people's lifestyles are caused by the ease of use of technology, especially in the entertainment sector. In the field of entertainment, music is certainly no stranger to society, from children to parents. With digital advances and internet technology, music can be heard by millions of music lovers from all over the world. Music applications can increase interest and attract user attention to continue using them or diminish because they are bored using them. Problems that often occur when listening to music include not being user friendly, prices are quite expensive especially for students or students and also the services provided are less attractive. This study aims to find out how to increase user interest and keep it interesting using a music application. Therefore, the author tries to design a music application, namely the Dengerin Application. This design uses the Design Thinking method because it can produce creative solutions. In testing using a usability testing system with a score of 77,5. The result of this research is the design of mobile-based “Dengerin” application interface ehich was designed using figma.","PeriodicalId":477061,"journal":{"name":"Komputa: Jurnal Ilmiah Komputer dan Informatika","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135303015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-05DOI: 10.34010/komputa.v12i2.10884
Helmi Nurhidayat, Moh. Ali Romli
Salah satu teknologi yang menggabungkan objek tiga dimensi ke lingkungan nyata secara real time adalah Augmented Reality (AR). Salah satu sektor bisnis yang mengalami perkembangan pesat adalah bisnis perumahan. Untuk memudahkan pelanggan dalam melihat spesifikasi dan contoh perumahan, diperlukan visualisasi objek 3D dengan fitur rotasi, yang memungkinkan pengguna untuk melihat interior setiap ruangan, serta mengubah warna rumah sesuai keinginan. Penelitian ini bertujuan untuk menerapkan teknologi Augmented Reality untuk katalog penjualan rumah di Perumahan Griya Permata 2 Tanjungsari. Hasil pengujian menggunakan metode blackbox testing telah selesai dilakukan pada aplikasi dan menunjukkan bahwa aplikasi ini berjalan sesuai dengan fungsionalitas yang direncanakan. Namun, hasil Test intensitas cahaya, oklusi, dan jarak lacak menunjukkan bahwa proses pendeteksian memengaruhi hasil deteksi marker. Jarak maksimal pendeteksian adalah 100 cm, di mana pada jarak tersebut aplikasi akan mengalami kesulitan dalam melacak objek dan marker tidak dapat dideteksi hingga oklusi mencapai 75%. Penerapan teknologi Augmented Reality merupakan langkah yang tepat untuk meningkatkan efektivitas pemasaran dalam bisnis perumahan. Penggunaan teknologi Augmented Reality memberikan pengalaman interaktif dan realistis bagi calon pembeli, membantu memperluas jangkauan pemasaran, dan dapat meningkatkan daya tarik katalog perumahan.
Kata kunci : Augmented Reality, Marker Based Tracking, Android, Media Pemasaran
{"title":"Implementasi Teknologi Augmented Reality Pada Katalog Perumahan Sebagai Media Pemasaran Berbasis Android","authors":"Helmi Nurhidayat, Moh. Ali Romli","doi":"10.34010/komputa.v12i2.10884","DOIUrl":"https://doi.org/10.34010/komputa.v12i2.10884","url":null,"abstract":"Salah satu teknologi yang menggabungkan objek tiga dimensi ke lingkungan nyata secara real time adalah Augmented Reality (AR). Salah satu sektor bisnis yang mengalami perkembangan pesat adalah bisnis perumahan. Untuk memudahkan pelanggan dalam melihat spesifikasi dan contoh perumahan, diperlukan visualisasi objek 3D dengan fitur rotasi, yang memungkinkan pengguna untuk melihat interior setiap ruangan, serta mengubah warna rumah sesuai keinginan. Penelitian ini bertujuan untuk menerapkan teknologi Augmented Reality untuk katalog penjualan rumah di Perumahan Griya Permata 2 Tanjungsari. Hasil pengujian menggunakan metode blackbox testing telah selesai dilakukan pada aplikasi dan menunjukkan bahwa aplikasi ini berjalan sesuai dengan fungsionalitas yang direncanakan. Namun, hasil Test intensitas cahaya, oklusi, dan jarak lacak menunjukkan bahwa proses pendeteksian memengaruhi hasil deteksi marker. Jarak maksimal pendeteksian adalah 100 cm, di mana pada jarak tersebut aplikasi akan mengalami kesulitan dalam melacak objek dan marker tidak dapat dideteksi hingga oklusi mencapai 75%. Penerapan teknologi Augmented Reality merupakan langkah yang tepat untuk meningkatkan efektivitas pemasaran dalam bisnis perumahan. Penggunaan teknologi Augmented Reality memberikan pengalaman interaktif dan realistis bagi calon pembeli, membantu memperluas jangkauan pemasaran, dan dapat meningkatkan daya tarik katalog perumahan.
 Kata kunci : Augmented Reality, Marker Based Tracking, Android, Media Pemasaran","PeriodicalId":477061,"journal":{"name":"Komputa: Jurnal Ilmiah Komputer dan Informatika","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135547234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-05DOI: 10.34010/komputa.v12i2.10602
Mardiansyah Mardiansyah, Firman Amir
Pengelolaan persediaan padi merupakan aspek penting yang perlu ditingkatkan oleh para pemangku kepentingan guna mencapai keseimbangan antara persediaan dan konsumsi beras. Bullwhip Effect (BE) telah menjadi perhatian khusus dalam rantai pasokan selama pandemi, terutama dengan adanya komponen permintaan musiman dan nonmusiman. Peramalan kebutuhan produksi padi diperlukan untuk mengatasi masalah dalam pengolahan data dan situasi di lapangan. Perangkat lunak seperti Production and Operations Management (POM) dapat digunakan untuk peramalan menggunakan logika fuzzy. Dalam era Industri 4.0, sustainable smart manufacturing menjadi hal yang penting. Proyeksi kebutuhan produksi beras nasional dilakukan dengan menggunakan metode moving average dan metode exponential smoothing. Pengujian akurasi dilakukan dengan peramalan menggunakan metode moving average dan exponential smoothing dengan data produksi padi tahun 2010-2019, kemudian hasil peramalan tahun 2020 dari kedua metode tersebut akan dibandingkan dengan data real dan akan diketahui metode mana yang paling mendekati data real. Tujuan utama penelitian ini adalah untuk membandingkan dua metode yaitu metode moving average dan metode exponential smoothing yang digunakan pada perangkat lunak berbasis fuzzy. Hasil pengujian akurasi peramalan produksi beras dengan menggunakan metode moving average dan exponential smoothing yang telah dilakukan menunjukkan bahwa metode moving average lebih akurat dengan selisih 1,0089% dari data sebenarnya, sedangkan metode exponential smoothing memiliki selisih 12,0051% dari data sebenarnya.
{"title":"Analisis Perbandingan Akurasi Metode Moving Average dan Metode Exponensial Smoothing dalam Memprediksi Kapasitas Produksi Padi Nasional","authors":"Mardiansyah Mardiansyah, Firman Amir","doi":"10.34010/komputa.v12i2.10602","DOIUrl":"https://doi.org/10.34010/komputa.v12i2.10602","url":null,"abstract":"Pengelolaan persediaan padi merupakan aspek penting yang perlu ditingkatkan oleh para pemangku kepentingan guna mencapai keseimbangan antara persediaan dan konsumsi beras. Bullwhip Effect (BE) telah menjadi perhatian khusus dalam rantai pasokan selama pandemi, terutama dengan adanya komponen permintaan musiman dan nonmusiman. Peramalan kebutuhan produksi padi diperlukan untuk mengatasi masalah dalam pengolahan data dan situasi di lapangan. Perangkat lunak seperti Production and Operations Management (POM) dapat digunakan untuk peramalan menggunakan logika fuzzy. Dalam era Industri 4.0, sustainable smart manufacturing menjadi hal yang penting. Proyeksi kebutuhan produksi beras nasional dilakukan dengan menggunakan metode moving average dan metode exponential smoothing. Pengujian akurasi dilakukan dengan peramalan menggunakan metode moving average dan exponential smoothing dengan data produksi padi tahun 2010-2019, kemudian hasil peramalan tahun 2020 dari kedua metode tersebut akan dibandingkan dengan data real dan akan diketahui metode mana yang paling mendekati data real. Tujuan utama penelitian ini adalah untuk membandingkan dua metode yaitu metode moving average dan metode exponential smoothing yang digunakan pada perangkat lunak berbasis fuzzy. Hasil pengujian akurasi peramalan produksi beras dengan menggunakan metode moving average dan exponential smoothing yang telah dilakukan menunjukkan bahwa metode moving average lebih akurat dengan selisih 1,0089% dari data sebenarnya, sedangkan metode exponential smoothing memiliki selisih 12,0051% dari data sebenarnya.
","PeriodicalId":477061,"journal":{"name":"Komputa: Jurnal Ilmiah Komputer dan Informatika","volume":"170 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135547233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-30DOI: 10.34010/komputa.v12i2.9454
Fritson Agung Julians Ayomi, Kania Evita Dewi
Twitter social media is often used to express one's emotions through tweets. Much research has been conducted on emotional analysis in the social media Twitter. Machine learning is a tool that is widely used to categorize emotions. However, an imbalance in the amount of data between classes is often a problem. So, this research aims to determine the performance of the combined Multinomial Naïve Bayes (MNB) and Synthetic Minority Oversampling Technique (SMOTE) methods for emotional analysis of tweets from the social media Twitter. Each tweet through data preprocessing in this research includes case folding, data cleaning, convert slangword, convert negation, tokenization, stopword removal, and stemming. For feature extraction the n-gram method is used and for feature weighting the term frequency method is used. Testing was carried out using K-Fold Cross Validation. Based on the test results, using SMOTE an average accuracy of 0.65 or 65% was obtained and an average f1-score value of 0.66 or 66%. Meanwhile, without SMOTE, an average accuracy of 0.64 or 64% was obtained and an average f1-score of 0.65 or 65%. Although in this study it can be shown that the results using SMOTE are 1% better in categorizing emotions. However, the results obtained are not optimal, and other methods of data balancing and machine learning still need to be studied.
{"title":"Analisis Emosi pada Media Sosial Twitter Menggunakan Metode Multinomial Naive Bayes dan Synthetic Minority Oversampling Technique","authors":"Fritson Agung Julians Ayomi, Kania Evita Dewi","doi":"10.34010/komputa.v12i2.9454","DOIUrl":"https://doi.org/10.34010/komputa.v12i2.9454","url":null,"abstract":"Twitter social media is often used to express one's emotions through tweets. Much research has been conducted on emotional analysis in the social media Twitter. Machine learning is a tool that is widely used to categorize emotions. However, an imbalance in the amount of data between classes is often a problem. So, this research aims to determine the performance of the combined Multinomial Naïve Bayes (MNB) and Synthetic Minority Oversampling Technique (SMOTE) methods for emotional analysis of tweets from the social media Twitter. Each tweet through data preprocessing in this research includes case folding, data cleaning, convert slangword, convert negation, tokenization, stopword removal, and stemming. For feature extraction the n-gram method is used and for feature weighting the term frequency method is used. Testing was carried out using K-Fold Cross Validation. Based on the test results, using SMOTE an average accuracy of 0.65 or 65% was obtained and an average f1-score value of 0.66 or 66%. Meanwhile, without SMOTE, an average accuracy of 0.64 or 64% was obtained and an average f1-score of 0.65 or 65%. Although in this study it can be shown that the results using SMOTE are 1% better in categorizing emotions. However, the results obtained are not optimal, and other methods of data balancing and machine learning still need to be studied.","PeriodicalId":477061,"journal":{"name":"Komputa: Jurnal Ilmiah Komputer dan Informatika","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135126667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：