Waste is goods / materials that have no value in the scope of production, where in some cases the waste is disposed of carelessly and can damage the environment. The Indonesian government in 2019 recorded waste reaching 66-67 million tons, which is higher than the previous year, which was 64 million tons. Waste is differentiated based on its type, namely organic and anorganic waste. In the field of computer science, the process of sensing the type waste can be done using a camera and the Convolutional Neural Networks (CNN) method, which is a type of neural network that works by receiving input in the form of images. The input will be trained using CNN architecture so that it will produce output that can recognize the object being inputted. This study optimizes the use of the CNN method to obtain accurate results in identifying types of waste. Optimization is done by adding several hyperparameters to the CNN architecture. By adding hyperparameters, the accuracy value is 91.2%. Meanwhile, if the hyperparameter is not used, the accuracy value is only 67.6%. There are three hyperparameters used to increase the accuracy value of the model. They are dropout, padding, and stride. 20% increase in dropout to increase training overfit. Whereas padding and stride are used to speed up the model training process.
<p>Ikan Gurami (<em>Osphronemus Goramy)</em> merupakan ikan yang banyak dibudidayakan dan dikomsumsi masyarakat ini menjadi sektor unggulan di beberapa wilayah kabupaten Banyumas. Ikan gurami yang dibudidayakan oleh masyarakat Banyumas, sebenarnya bukan tanpa hambatan. Salah satu hambatan bagi peternak gurami adalah penyakit yang disebabkan oleh bakteri. Pada penelitian ini penulis membuat sistem pakar untuk mendiagnosis penyakit ikan Gurami yang disebabkan bakteri. Penelitian ini menggunakan metode<em> Case Based Reasoning</em> dan <em>Similarity</em> <em>Nearest Neighbor</em> untuk mendapatkan solusi yang terbaik dari kasus yang di identifikasi. Metode tersebut membandingkan antara kasus lama dengan kasus baru dan menghitung suatu nilai <em>similarity </em>kasus. Nilai <em>similarity</em> tertinggi dapat dijadikan kesimpulan untuk kasus yang paling mirip dengan diagnosa pakar. Sehingga dari kedua metode tersebut dapat dihasilkan sistem pakar yang dapat mendiagnosis dan menganalisis sesuai dengan nilai kemiripan gejala terhadap penyakit, serta menampilkan solusi penanganan dari penyakit yang didiagnosis. Hasil pengujian antar kasus dan sistem menggunakan perhitungan <em>similarity</em> mencapai nilai terbaik yaitu 100%. Hasil pengujian akurasi sistem untuk diagnosis yang sesuai dengan pikiran pakar, memperoleh hasil sebesar 93,33% dari 30 kasus yang diuji dengan sistem. Kesimpulan dari hasil tersebut adalah sistem dapat dikatakan layak untuk mendiagnosis penyakit Gurami yang disebabkan bakteri sesuai dengan yang dipikirkan pakar.</p><p> </p><p><em><strong>Abstract</strong></em></p><p><em>Gurami (Osphronemus Goramy) is a fish that is widely cultivated and consumed by the community. This fish is a leading sector in several regions of Banyumas district. Gouramy which is cultivated by the Banyumas people, is actually not without obstacles. One obstacle for gouramy breeders is a disease caused by bacteria. Reporting from the online news portal, circulating in February 2018 circulated that news about Gurami farmers was losing money because thousands of broodstock fish that had been raised to death were attacked by bacterial diseases, namely Aeromoniasis. Experts who handle this are limited, namely only 2 people in the Banyumas Regency.</em><em> </em><em>In this study the authors made an expert system to diagnose Gurami fish disease caused by bacteria. This study uses the Case Based Reasoning (CBR) and Nearest Neighbor methods used to get the best solution from the identified case. The CBR method compares the old case with the new case and calculates a case similarity value. The system was built with 13 symptoms and 3 Gurami diseases caused by bacteria. Each symptom each has a weight of 5, 3, and 1. The highest similarity value can be used as a conclusion for the case most similar to the expert diagnosis. So that from these two methods an expert system can be produced that can diagnose and analyze according to the similarity of symptoms to the disease, as well as display solutions to the treatment of diagnosed diseases. The test results are between cases and the system uses the similarity calculation to achieve the best value of 100%. The results of the system accuracy test for diagnoses that are in accordance with the expert's mind, obtained results of 93.33% from 30 cases tested with the system. The conclusion of these results is that the system can be said to be feasible to diagnose Gurami disease caused by bacteria according to what experts think.</em></p><p><em><strong><br /></strong></em></p>
Mobile learning is the intersection of Mobile Computing and E-Learning that provides the resources that can be accessed from anywhere, a powerful search system capabilities, rich interaction, full support for effective learning and assessment based on performance. E-learning has the characteristics are independent of place and time. Education requires an alternative model of learning has not characteristic depending on location and time. In addition to the proficiency level, an alternative model is also expected to provide knowledge sharing and visualization facilities of knowledge so that knowledge becomes more interesting and easy to understand. Mobile learning application built to run on android operating system. Android operating system was chosen because it has mastered the current android smartphone market and is an open source operating system that is easy to develop. Android versions that support this application is version 2.2 to 4.2. Using jQuery mobile framework allows users to access the M-Learning. Because besides its attractive, jQuery mobile display can also customize the display of the mobile device.
Sebuah perangkat lunak dikatakan siap untuk dipakai apabila sudah melalui tahap pengujian. Pada era pengembangan perangkat lunak dengan metodologi tradisional, pengujian dilakukan dengan cara mencoba satu persatu menu aplikasi ketika aplikasi yang dikembangkan sudah jadi. Cara pengujian tersebut akan membutuhkan waktu yang lama apabila developer mengerjakan proyek perangkat lunak dalam skala besar. Selain itu, cara tersebut juga tidak dapat menguji logika dan method dari suatu kelas. Salah satu metode pengembangan perangkat lunak yang dapat menghemat waktu pengujian, namun fungsionalitasnya tetap terjaga adalah test driven development (TDD). Pada metode TDD, pengembangan perangkat lunak dilakukan dengan membuat test case terlebih dahulu baru kemudian melakukan producing code. Pada penelitian ini, dikembangkan sebuah aplikasi web menggunakan TDD. Aplikasi web yang dikembangkan adalah berupa sistem informasi mengenai ulasan film lokal indonesia atau disebut Indonesia Movie Database (IMDB). Bahasa pemrograman web yang dipakai adalah ruby dengan menggunakan framework rails. Sedangkan alat yang dipakai untuk pengujian adalah Rspec. Hasil implementasi TDD membuktikan bahwa fungsi-fungsi dari aplikasi web yang dibangun dapat berkerja dengan baik. Selain itu kode program yang dihasilkan juga menjadi rapi dan mudah dibaca oleh pengembang lain karena menerapkan refactoring. Pengujian unit test menggunakan Rspec membantu pengembang dalam menangani kesalahan dan memudahkan menambah fitur baru dari aplikasi web.
Indonesia is a tropical country that has various skin diseases. Tinea versicolor, ringworm, and scabies are the most common types of skin diseases suffered by the people of Indonesia. The classification of the three skin diseases can be automatically completed by artificial intelligence and deep learning technology because the classification process using an expert will require a lot of money and time. The challenge in classifying skin diseases is in the process of collecting data. Because health data cannot be obtained freely, there must be approval from the patient or hospital. Therefore, to overcome the limited amount of data, Pre-Trained CNN is used. The Pre-Trained CNN model has many patterns from thousands of images, so we do not need many images to train the model. In this study, a comparison of five pre-trained CNN models was conducted, namely VGGNet16, MobileNetV2, InceptionResNetV2, ResNet152V2, and DenseNet201. The aim is to find out which CNN model can produce the best performance in classifying skin diseases with a limited amount of image data. The test results show that the ResNet152V2 model has the best classification ability with the highest accuracy, precision, recall, and F1 score values, namely 95.84%, 0.963, 0.96, and 0.956. As for the training execution time, the ResNet152V2 model has the fastest time to achieve 95% accuracy. That's happened because the addition of the dropout parameter is 20%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.