24 research outputs found
Deep learning on curriculum study pattern by selective cross join in advising students' study path
No full textSistem Deteksi Wajah Pada Kamera Realtime dengan menggunakan Metode Viola Jones
No full textIn general, human are given the mind and mind to be able to determine or be able to didtinguish individuals who appear either human, animal, plant, and other objects that are known or unknown. And it is possible for human to recognize these object from their sight and from their brain memory. Especially on the human face, human can recognize whether the object is human or not human, and can recognize the object very well through his own eyes.face detection system in human becomes very important in the development of science of digital image processing. The research has been done with many advantages and disadvantages. From a face many information features that can be read, such as eyes, nose, and mouth. The detection system uses Viola Jones method as an object detection method. The Viola Jones method is known to have considerable Speed and accuracy as it combines several concepts (Haar feature, Integral image, Adaboost, Cascade classifier) into a main method for detecting objects.Based on tests conducted on face identification under conditions that may affect face detection results, the results show an accuracy of 67,6 % to detect the face
Deteksi Kendaraan secara Real Time menggunakan Metode YOLO Berbasis Android
Get PDFThe Activities on the highway that involve vehicles often have congestion problems due to the tightening of the quantity of vehicles on the highway. In addition, there are also problems of order and violations, the use of improper routes, such as vehicles entering the lane that are not intended for the vehicle. Therefore, researchers designed a vehicle detection application in real time based on Android using the YOLO method (You Only Look Once). The analysis carried out using 200 datasets, 4 classes, 10 batches, and 200 epochs. The training process was carried out up to 4000 steps, and the storage of checkpoints to the form of file protob was done at steps 800, 1000, 1200, 1400, 1600, 1800, 2000, 3000, and 4000. Bounding boxes successfully detected and classified objects correctly. This test is done using a Xiaomi Redmi 4X smartphone with a video resolution measuring 768x432 pixels
Open API untuk Warung Makan Usaha Kecil dan Industri Rumahan
Get PDFMany food stalls are small businesses or home industries with a capital under 10 million rupiah and are generally located in the yard of the stall owner, and do not have branches. The most common obstacle was the lack of customers caused by the location of the stall which was not strategic and the information about the stall service was not widespread. OPEN API Warung Makan is the implementation of Community Service activities funded from an internal grant 2019 Raja Ali Haji Maritime University. This API is intended to be open to any application developer to take advantage of this free service to be aimed at food stalls that fall into the category of small businesses or home industries. OPEN API Warung Makan provides two parts of service, namely for customers and stall owners. OPEN API Warung Makan uses Raja Ali Haji Maritime University\u27s cloud infrastructure and does not require Authentication Tokens or the like.Usaha Warung Makan banyak yang merupakan usaha kecil atau industri rumahan merupakan warung makan dengan modal dibawah 10juta rupiah dan umumnya terletak pada halaman pekarangan dari pemilik warung, serta tidak memiliki cabang. Kendala paling banyak di jumpai adalah sepinya pelanggan yang di sebabkan oleh lokasi warung yang tidak strategis serta tidak meluasnya informasi layanan warung itu sendiri. OPEN API Warung Makan merupakan pelaksanaan kegiatan Pengabdian Kepada Masyarakat dengan bantuan hibah internal 2019 Universitas Maritim Raja Ali Haji. API ini dimaksudkan untuk terbuka terhadap developer aplikasi manapun untuk memanfaatkan fasilitas gratis ini untuk ditujukan kepada usaha warung makan yang masuk ke dalam kategori usaha kecil atau industri rumahan. OPEN API Warung Makan menyedikan dua bagian layanan yakni untuk pelanggan dan pemilik warung. OPEN API Warung Makan menggunakan infrastruktur cloud Universitas Maritim Raja Ali Haji dan tidak memerlukan Authentication Token atau sejenisny
Otomatisasi Pendeteksi Kata Baku dan Tidak Baku pada Data Twitter Berbasis KBBI
Get PDFPenelitian ini mengembangkan sistem deteksi otomatis kata-kata baku dan non-baku pada data Twitter berbasis Kamus Besar Bahasa Indonesia (KBBI). Twitter merupakan platform media sosial yang populer, namun sering kali digunakan dengan kata-kata tidak baku yang mengganggu komunikasi. Normalisasi kata-kata tidak baku diperlukan untuk pemrosesan dan analisis tweet. Penelitian sebelumnya menggunakan metode Levenshtein Distance dan pengklasifikasi Naïve Bayes, serta Term Based Random Sampling dalam proses Stopword Removal. Preprocessing penting dalam klasifikasi teks di media sosial. Penelitian ini fokus pada preprocessing dan deteksi kata-kata baku dan non-baku pada data Twitter menggunakan KBBI. Sistem otomatis ini membantu peneliti mencari kata-kata non-baku atau slang dengan mudah, meningkatkan kualitas komunikasi, dan pemahaman pesan di data Twitter yang mencerminkan tren bahasa yang berkembang. Penelitian ini juga memperkenalkan pendekatan yang terstruktur untuk mengotomatisasi deteksi kata-kata baku dan non-baku, dengan langkah-langkah yang meliputi pengumpulan data, preprocessing data, identifikasi bahasa tidak baku, penghapusan kata berimbuhan, dan identifikasi kata slang. Metode ini mendukung analisis sentimen dalam text mining dan memastikan hasil klasifikasi sentimen yang lebih akurat dalam data Twitter. Berdasarkan pengujian, langkah-langkah preprocessing meningkatkan performa metode penentuan polarity dengan accuracy InSet sebesar 66,66% dan F1-score sebesar 61,40%.Penelitian ini berfokus pada pengembangan sistem deteksi otomatis untuk membedakan kata baku dan tidak baku pada data Twitter, berdasarkan Kamus Besar Bahasa Indonesia (KBBI). Karena Twitter merupakan platform media sosial yang sering menggunakan kata-kata yang tidak baku, penelitian ini penting untuk memastikan komunikasi yang efektif. Melalui normalisasi kata-kata tidak baku, penelitian ini berkontribusi signifikan terhadap pra-pemrosesan dan analisis tweet, yang merupakan langkah penting dalam klasifikasi teks media sosial. Sistem otomatis yang dikembangkan tidak hanya membantu peneliti dengan mudah mengidentifikasi penggunaan kata-kata slang atau tidak baku, namun juga meningkatkan kualitas komunikasi dan pemahaman pesan dalam tweet yang mencerminkan tren bahasa terkini. Pendekatan yang dilakukan dalam penelitian ini meliputi langkah-langkah seperti pengumpulan data, preprocessing, identifikasi bahasa tidak baku, penghapusan kata berimbuhan, identifikasi slang, dan penggunaan metode lexicon-based untuk kamus opini. Pendekatan ini efektif dalam mendukung analisis sentimen pada teks mining dan memastikan hasil klasifikasi sentimen pada data Twitter lebih akurat. Hasil percobaan menunjukkan bahwa langkah preprocessing tersebut berhasil meningkatkan akurasi metode penentuan polarisasi, dengan tingkat akurasi InSet sebesar 66,66% dan F1-score sebesar 61,40%.
Abstract
This research focuses on developing an automatic detection system to distinguish between standard and nonstandard words in Twitter data, based on the Kamus Besar Bahasa Indonesia (KBBI). As Twitter is a social media platform that often uses nonstandard words, this research is important to ensure effective communication. Through the normalization of nonstandard words, this research contributes significantly to the pre-processing and analysis of tweets, which is an important step in social media text classification. The automated system developed not only helps researchers easily identify the use of slang or nonstandard words, but also improves the quality of communication and message understanding in tweets that reflect current language trends. The approach taken in this research includes steps such as data collection, preprocessing, nonstandard language identification, removal of affixed words, slang identification, and the use of lexicon-based methods for opinion dictionaries. This approach is effective in supporting sentiment analysis in text mining and ensures more accurate sentiment classification results on Twitter data. Experimental results show that these preprocessing steps successfully improve the accuracy of the polarization determination method, with an InSet accuracy rate of 66.66% and F1-score of 61.40%
Predictive Adaptive Test with Selective Weighted Bayesian Through Questions and Answers Patterns to Measure Student Competency Levels
Get PDFComputer Assisted Testing (CAT) system in Indonesia has been commonly used but only to displaying random exam questions and unable to detect the maximum performance of the test participants. This research proposes a simple way with a good level of accuracy in identifying the maximum ability of test participants. By applying the Bayesian probabilistic in the selection of random questions with a weight of difficulties, the system can obtain optimal results from participants compared to sequential questions. The accuracy of the system measured on the choice of questions at the maximum level of the examinee alleged ability by the system, compared to the correct answer from participants gives an average accuracy of 75% compared to 33% sequentially. This technique allows tests to be carried out in a shorter time without repetition, which can affect the fatigue of the test participants in answering questions
Bisnis Online UMKM melalui Aplikasi E-Commerce untuk Pemasaran di Tengah Pandemik: Online Business UMKM with E-Commerce for Marketing during a Pandemic
No full textDalam situasi pandemic covid 19 seperti sekarang ini kami berfikir, bagaimana meningkatkan kesejahteraan UMKM pada bisnis Donat Mini (Domi) dengan tetap mematuhi protokol kesehatan. Maka kami membuatkan aplikasi E-Commerce dimana pemasaran akan dilakukan secara online. Dengan adanya sistem aplikasi E-Commerce ini nantinya akan memudahkan UMKM Domi dan masyarakat untuk tetap bisa melakukan transaksi jual-beli tanpa harus bertatap muka dan berkerumun antri di toko. Dengan begitu protokol kesehatan dapat dijaga untuk menjaga jarak dan kebutuhan konsumen terpenuhi. Aplikasi E-Commerce ini memiliki berbagai fitur fungsi utama antara lain adalah memberikan layanan teknis, informasi, dan promosi tentang jenis usaha yang diperjualkan kepada masyarakat. Aplikasi E-Commerce ini juga menjadi jembatan bagi masyarakat sebagai pemanfaatan teknologi dalam memenuhi kebutuhan.Dalam situasi pandemic covid 19 seperti sekarang ini kami berfikir, bagaimana meningkatkan kesejahteraan UMKM pada bisnis Donat Mini (Domi) dengan tetap mematuhi protokol kesehatan. Maka kami membuatkan aplikasi E-Commerce dimana pemasaran akan dilakukan secara online. Dengan adanya sistem aplikasi E-Commerce ini nantinya akan memudahkan UMKM Domi dan masyarakat untuk tetap bisa melakukan transaksi jual-beli tanpa harus bertatap muka dan berkerumun antri di toko. Dengan begitu protokol kesehatan dapat dijaga untuk menjaga jarak dan kebutuhan konsumen terpenuhi. Aplikasi E-Commerce ini memiliki berbagai fitur fungsi utama antara lain adalah memberikan layanan teknis, informasi, dan promosi tentang jenis usaha yang diperjualkan kepada masyarakat. Aplikasi E-Commerce ini juga menjadi jembatan bagi masyarakat sebagai pemanfaatan teknologi dalam memenuhi kebutuhan
Building Student’s Study Path using Markov Chain Process with Apriori Cross Join Pearson Correlation
Get PDFStudent’s study path could be advised by using bestpossible path from Markov Chain rule based on student’sacademic performance records with several assumption on thecurrent curriculum. Finding the Markov’s rule is crucial processbecause it will determine study path’s scenarios which rely onstudent current performance to choose the next best possiblepath. The rule would be built using the whole student’s academicperformance on the same curriculum by implementing AprioriCross Join Pearson Correlation Test on two consecutivesemesters. It will then create path consist of paired courses A->B with Pearson value that would be implemented as rule in Markov Proces
Implementation of Model View Controller Architecture in Designing Outcome-Based Education (OBE) Curriculum Management Information System
No full textThe development of 21st century education demands the integration of practical and collaborative skills that are relevant to global needs, where the Outcome-Based Education (OBE) approach is the key to achieving measurable and clear learning outcomes. This study focuses on the design of an OBE-based curriculum management information system by implementing the Model View Controller (MVC) architecture and the Laravel framework which aims to overcome the constraints of manual curriculum management at Universitas Maritim Raja Ali Haji, which requires significant time to collect, organize, and analyze data, thus hampering lecturer productivity and interaction with students. The development of the system not only integrates various components of the OBE curriculum, but also creates a collaborative platform in curriculum management. Based on the results of the study that have gone through usability testing with the explorative test method, involving all sub-system designers and stakeholders, this system shows a high level of effectiveness, efficiency, and user satisfaction. Thus, this study is expected to improve the efficiency and effectiveness of OBE curriculum management, which contributes to improving the quality of education at the institution
Implementation of Model View Controller Architecture in Designing Outcome-Based Education (OBE) Curriculum Management Information System
Get PDFThe development of 21st century education demands the integration of practical and collaborative skills that are relevant to global needs, where the Outcome-Based Education (OBE) approach is the key to achieving measurable and clear learning outcomes. This study focuses on the design of an OBE-based curriculum management information system by implementing the Model View Controller (MVC) architecture and the Laravel framework which aims to overcome the constraints of manual curriculum management at Universitas Maritim Raja Ali Haji, which requires significant time to collect, organize, and analyze data, thus hampering lecturer productivity and interaction with students. The development of the system not only integrates various components of the OBE curriculum, but also creates a collaborative platform in curriculum management. Based on the results of the study that have gone through usability testing with the explorative test method, involving all sub-system designers and stakeholders, this system shows a high level of effectiveness, efficiency, and user satisfaction. Thus, this study is expected to improve the efficiency and effectiveness of OBE curriculum management, which contributes to improving the quality of education at the institution
