EXPERT
Not a member yet
201 research outputs found
Sort by
Klasifikasi Penggunaan Masker dengan Convolutional Neural Network Menggunakan Arsitektur MobileNetv2
Get PDFIn the current pandemic situation caused by the COVID-19 virus. The spread of the virus comes from droplets or splashes attached to objects or public facilities. The use of masks is an effort to minimize the spread of this virus. The use of masks is required when carrying out activities in public places that allow spread. However, there are still people who are ignorant of this, so there must be officers who carry out supervision to bring order to the community so that they always wear masks. Classification by using Deep Learning to detect the use of masks is one way to help bring order to the community and assist officers in conducting surveillance. In this research, the Deep Learning model is made using the Convolutional Neural Network method and the MobileNetv2 architecture. The selection of this method is based on the effectiveness of the method in resource utilization that is not too heavy and can produce maximum accuracy. The dataset used is sourced from an open. The results of the model test for real-time mask detection succeeded in detecting objects in 2 classes, namely, mask and without a mask, and displayed excellent and accurate results with an average value of 0.99 on precision, recall, f1-score, and support
Chatbot Menggunakan Natural Language Processing untuk Pembelajaran Bahasa Inggris Berbasis Android
Get PDFLearning languages nowadays is massive and varies, therefore the interest in learning keeps increasing. But there are some limitations that cause students not to try to learn something, such as the matter of time and the fear of pronouncing and speaking a foreign language whether to people they know or do not know. Therefore, this smart English language learning application is one of the solutions as a platform for learning and practice. This application uses a Natural Language Processing (NLP) method that can act as a friend to practice speaking, especially English. This research is an option for learning languages that is more interactive and fun
Strategi Pemilihan Lokasi Usaha dengan Pendekatan MOORA
Get PDFOne of the business strategies is to determine the location of the business, as well as a determining factor and very important in getting the best results in its business. Currently, there are many business locations that can be an alternative to running a business, such as the existence of new buildings being built, and the existence of housing that can bring business closer to the market. Taking this into account, business actors must be able to consider whether the location will be strategic or not. There are several considerations that can be taken by business owners, including building area, surrounding competitors, proximity to the market, available facilities, and rental prices. By paying attention to these things, apart from making criteria for choosing alternative business locations, it will also avoid losses for business actors by determining business locations that generate maximum profits. In this study, the author uses Multi-Objective Optimization on The Base Method of Ratio Analysis (MOORA) to determine the choice of the business location and as a strategy to develop its business. The author uses 5 criteria to choose 5 alternative business locations. Based on the calculation stages in the MOORA method, an alternative business A2, located in MGT Blok H, is generated, which is the best value from all alternative locations and is chosen as a business location that will provide business continuity, and will provide benefits in running its business
Penyelarasan Sistem Tata Kelola pada PT. MEI dengan Menggunakan Cobit 2019
Get PDFPT. MEI is a consulting company providing human resources and management of human resource functions, one of the programs implemented is the Domestic Apprenticeship program, to carry out these business processes. PT. MEI already has an information system but it is not optimal and is named (Apprenticeship Administration Information System). Therefore the use of COBIT Design Toolkit 2019 aims to help PT. MEI in aligning the governance system so that it is well mapped and ensures that IT achievements are aligned with the management and business environment in the company. This study aims to design a Governance Design based on the 2019 Cobit Design Toolkit The method used is to utilize the Cobit 2019 design factor, this study produces recommendations for the use of the priority core model and the competency level of PT. MEI The results of this study will be based on 31 core models or processes that need to be run with level 1 capabilities, two core samples or processes that need to be run with level 2 capabilities, four core models or processes that need to be run with level 3 capabilities, and two models or core competency processes that need to be implemented with competency level 4. Companies must conduct an assessment of the main point stage model According to the results of this study to ensure that business processes operate optimally. The core model evaluation phase must be done by level of importance put forward by the 2019 COBIT design factors as a follow-up to the findings of this study
Sistem Pendukung Keputusan Menggunakan WASPAS dalam Menentukan Rumah Kost yang Strategis
Get PDFA boarding house is a place to stay temporarily when you have to be away from your house or the area where you live. In Indonesia, there are many students who, after graduating from high school or the equivalent, continue their studies outside the city, some even outside the province or island. The choice to continue their studies outside the area is based on several reasons, including because the majors desired and in accordance with their interests and talents are not available in their area of origin. Therefore, leaving the area or city of birth and settling in the area or city where the desired university is located must be an option. The development of a campus or college has an impact on the increasing demand for property by consumers, especially the need for boarding houses. Based on this background, it is necessary to determine strategic boarding houses using the Waspas method. The results of the calculations in determining strategic boarding houses are: 1. Melati boarding house (Q3) 8,700, 2. Anyelir boarding house (Q1) 6,342, 3. Orchid boarding house (Q4) 5,688, 4. Mawar boarding house (Q2) 5,502 . 5. Akasia boarding house (Q5) 5,125
Sistem Informasi Korespondensi Rekam Medis di Rumah Sakit Menggunakan Microsoft Visual Studio
Get PDFTechnological developments in communication systems are still used by humans. From traditional methods to using modern methods in accordance with current technological developments. One way to communicate using traditional methods that are still used today is by using letters. Medical record correspondence is an activity of correspondence related to patient medical record information in this case at the hospital, namely making letters to be treated, letters to request diagnosis, letters to carry out treatment, letters to finish treatment, and letters to death. Making letters, still manually using Microsoft Word. The process of making a certificate takes 1-2 days, so it is necessary to have an information system that can speed up the making of a certificate to be more efficient and effective. The design method uses the SDLC method. The stages of the method are planning (planning), analysis (analysis), design (design), implementation (implementation), and system maintenance (maintenance), the correspondence information system that has been created can be concluded that the system can facilitate officers in making certificates and can also speed up the creation of letters.Abstrak - Perkembangan teknologi pada sistem komunikasi yang masih terpakai oleh manusia. Dari metode yang tradisional hingga menggunakan metode yang modern yang sesuai dengan perkembangan teknologi saat ini. Salah satunya dengan cara berkomunikasi menggunakan metode tradisional yang masih dipakai pada saat ini adalah dengan menggunakan surat. Korespondensi rekam medis adalah suatu kegiatan dari surat menyurat yang berhubungan dengan informasi rekam medis pasien dalam hal ini di Rumah Sakit yaitu pembuatan surat untuk dirawat, surat untuk meminta diagnosa, surat untuk menjalankan pengobatan, surat untuk selesai pengobatan, dan surat untuk kematian. Pembuatan surat, masih secara manual dengan menggunakan Microsoft Word. Proses pembuatan surat keterangan memakan waktu 1-2 hari, sehingga diperlukan adanya sistem informasi yang dapat mempercepat pembuatan surat keterangan agar lebih efisien dan efektif. Metode perancangan menggunakan metode SDLC. Tahapan metode adalah perencanaan (planning), analisis (analysis), perancangan (design), implementasi (implementation), dan pemeliharaan sistem (maintenance), sistem informasi korespondensi yang telah dibuat ini dapat disimpulkan bahwa sistem tersebut dapat memudahkan petugas dalam pembuatan surat keterangan dan juga dapat mempercepat dalam pembuatan surat
Perancangan Sistem Informasi Kunjungan Pasien Rawat Jalan di Rumah Sakit Muhammadiyah Bandung
Get PDFThe purpose of this study was to determine the patient visit information system at this hospital. By using qualitative research methods with a descriptive approach through observation, interviews, and literature studies, while for its development using the waterfall method through the stages of needs analysis, design, coding, implementation, and system testing which is carried out sequentially. This information system was created using Microsoft Visual Studio for databases using Microsoft Access. The problem that occurred in the previous system was that the data processing was still using Microsoft Excel so that the officer's data processing took a long time because it had to be done manually and had not been well integrated. With the information system designed, it is hoped that it can assist officers in processing patient visit data, and can also simplify and speed up officers in making outpatient visit reports because the information system designed is more effective and efficient. The conclusion of this outpatient visit information system design is that the information system is made more integrated and neatly organized
Penerapan Case-based Reasoning (CBR) pada Sistem Pakar Diagnosis Penyakit Tanaman Pangan
Get PDFThis study discusses an expert system for diagnosing food plant diseases by applying Case-based Reasoning (CBR). CBR is a way of thinking about computer reasoning by utilizing past knowledge to handle new cases. CBR resolves new cases by observing the old cases that are closest to the new cases. The diagnosis stage begins with entering new cases with their symptoms to be diagnosed into the system, after that calculating the similarity value of new cases with existing cases on a case basis with the nearest neighbor algorithm. Based on testing using test data with a similarity threshold of 70%, the system produces performance with a sensitivity of 100% and an average accuracy rate of 76, 74%. This proves that the system works well for diagnosing food plant diseases (rice, cassava, corn, and peanuts).Abstrak - Penelitian ini membahas tentang sistem pakar diagnosis penyakit tanaman pangan dengan menerapkan Case-based Reasoning (CBR). CBR merupakan cara berpikir bernalar komputer dengan memanfaatkan pengetahuan yang lalu untuk menangani kasus baru. CBR menyelesaikan kasus baru dengan mengamati kasus lama yang terdekat dengan kasus baru. Tahapan diagnosis diawali dengan mengentrikan kasus baru dengan gejalanya yang akan didiagnosis ke dalam sistem, setelah itu menghitung nilai kemiripan kasus baru dengan kasus-kasus yang ada pada basis kasus dengan algoritma nearest neighbor. Berdasarkan pengujian menggunakan data uji dengan ambang kemiripan sebesar 70% maka sistem menghasilkan performa dengan sensitivitas 100% dan tingkat akurasi rata-rata 76, 74%. Hal ini membuktikan bahwa sistem bekerja dengan baik untuk mendiagnosis penyakit tanaman pangan (padi, singkong, jagung, dan kacang tanah)
Komparasi Metode Simple Additive Weighting dan Analytical Hierarchy Process dalam Rekomendasi Penyewaan Pakaian
Get PDFClothing is used as a symbol of the wearer's position. This requires people to follow the lifestyle of clothing trends. Clothing trends today change very quickly and tend to be relatively short-lived. As a result of these changes, people are encouraged to become consumptive. Now people can enjoy it without having to buy expensive clothes. Branded clothes can also be used cheaply. Therefore, clothing rental is a stylish yet fashionable option. There are many clothing rentals shops today, but there is no specific information for renters who are looking for a rental shop that fits their needs. People tend to search and visit rental locations to rent clothes. This rental recommendation makes it easier for tenants to find clothes according to their own criteria. The purpose of this study was to compare the SAW-AHP method which was most suitable for the case of this study. After calculating and comparing the two methods, the SAW method is suitable for this case because it can count all samples, while the AHP method can only count 15 samples according to the Random Index table
Peran Big Data dan Deep Learning untuk Menyelesaikan Permasalahan Secara Komprehensif
Get PDFPeran sain data besar (Big Data) dan pembelajaran mesin dewasa ini tidak dapat terelakkan terutama untuk menganalisis data dan memberikan kecerdasan pada komputer agar bekerja secara otonom untuk menyelesaikan suatu pekerjaan tertentu. Perkembangan teknologi sensor dan internet membuat ketersediaan data tersebut melimpah yang selanjutnya dapat dilakukan analisis data dalam jumlah yang besar. Hal tersebut mempengaruhi bagaimana cara pandang komputasi dalam berbagai macam bidang baik ilmu alam maupun sosial. Data yang terkumpul dapat berupa beragam format dengan laju pertambahan yang cepat dan dinamis. Kita perlu algoritma atau model yang mumpuni untuk memahami dan menggali pengetahuan pada set data yang besar tersebut beserta rancangan modelnya yang secara otomatis mempunyai kemampuan memprediksi atau mendeteksi. Deep Learning dengan kapasitasnya yang besar serta hubungan korelasi antar neuron yang sangat banyak diharapkan mampu menjawab tantangan tersebut didukung oleh beberapa penelitian terkini pada penerapannnya di berbagai bidang keilmuan. Dalam paper ini akan dipaparkan contoh pemanfaatan Deep Learning pada Big Data yang telah kita lakukan pada pengenalan video aksi manusia pada Youtube, Segmentasi pada sel berskala besar, citra dada x-ray dan data time-series multi variabel hubungannya dengan pandemi COVID-19