JTIM : Jurnal Teknologi Informasi dan Multimedia
Not a member yet
290 research outputs found
Sort by
Pemeriksaan Pola Kalimat Otomatis Pada Sebuah Karangan Menggunakan POS Tagging Bahasa Indonesia Dan LALR Parser
No full text Dalam era perkembangan teknologi yang pesat ini, berbahasa mempunyai peran penting dalam kehidupan sehari-hari seperti untuk berkomunikasi dengan sesama secara lisan maupun tulisan. Komunikasi akan berlangsung dengan baik jika bahasa yang digunakan dapat dipahami sehingga pesan dapat tersampaikan. Dalam komunikasi tulisan, keterampilan menulis diperlukan untuk menghasilkan tulisan yang dapat menyampaikan pesan dengan baik. Salah satu bentuk hasil dari keterampilan menulis adalah sebuah karangan. Penulisan karangan harus memperhatikan kaidah pemakaian bahasa yaitu fonologi, morfologi, dan sintaksis. Pentingnya kaidah tersebut khususnya sintaksis atau struktur dan pola kalimat dapat mengungkapkan ide yang dapat tersampaikan dengan baik dan mudah untuk dipahami melalui karangan. Penelitian ini bertujuan untuk membantu dalam memeriksa pola kalimat pada sebuah karangan secara otomatis. Dalam pemeriksaan ini diimplementasikan dengan bahasa pemrograman python pada jupyter notebook menggunakan library nltk untuk proses preprocessing, library flair nlp untuk proses part of speech tagging bahasa Indonesia dan penggunaan tabel lalr parser untuk pemeriksaan pola kalimat. Pola kalimat yang digunakan pada pemeriksaan ini adalah S-P, S-P-O, S-P-K, S-P-O-K, S-P-Pel-K, dan S-P-O-Pel-K. Hasil dari penelitian ini adalah berupa pemeriksaan pola kalimat otomatis pada sebuah karangan sederhana dengan batasan menggunakan kalimat tunggal dan kalimat aktif. Pemeriksaan ini dapat memeriksa 14 dari 16 kalimat pada karangan dengan nilai keberhasilan sebesar 87,5% dan nilai keakuratan sebesar 62,5%. Faktor yang mempengaruhi hasil tersebut adalah variasi komponen pola kalimat yang masih terbatas dan penggunaan flair nlp dalam proses pos tagging yang dapat menghasilkan label jenis yang berbeda pada suatu kata yang dipengaruhi oleh letak posisi kata tersebut pada sebuah kalimat
Desain Scanner untuk Digitalisasi Naskah Lontar Aksara Sasak dengan Smart Phone Menggunakan Black Box Testing
No full textLontar is one of the cultural heritages that has information about the history of the Sasak civilization in Lombok, NTB in the past. The problem currently being faced is the lontar which is not well maintained. While the lontar used as Sasak script will wear out soon, because it is not durable. Utilization of technology is one of the media that can be used as a solution to overcome these problems. The process of digitizing letters is carried out. The use of technology will make the lontar into a digital form and will not be obsolete if the lontar is stored for a long time and the information contained in the lontar can be protected for a long time. This study presents the reconstruction of the Ancient Sasak Lontar Manuscript using scanning technology, which is used to obtain point cloud data from ancient structures, and modeling methods built using point cloud data. This study describes the use of the point cloud data acquisition process using terrestrial and native measurement point cloud measurements (to eliminate point noise, smoothing, data registration, object extraction, and so on.) the information is correct and the target structure is complete, and then builds a Sasak ejection surface model of triangular meshes, texture mapping of real models obtained through photographs. Testing is done by black box testing and all data entered is tested with various data that are not in accordance with the rules. Black Box Testing is done by testing scanners and applications without seeing/knowing the internal structure of the scanner and software
Implementasi Metode Regresi Linier Pada Rancang Bangun Sistem Informasi Monitoring Nutrisi Tanaman Hidroponik Kangkung
No full textHydroponics is the cultivation of plants without using soil. Hydroponic flowers, herbs and vegetables are grown in a moist growing medium and supplied with a solution rich in nutrients, oxygen and water. In the application of hydroponics, nutrition is a need that must always be met for plant development where each plant requires different nutrients. Nutrient Film Technique (NFT) is a technique that is often used in hydroponic cultivation. Because in this method the circulation of nutrients contained in the water will always flow through the plant at any time. So that plant growth is faster, because plants get oxygen and nutrients all the time. The NFT technique is said to be an energy-intensive technique, because the water pump will run continuously and still use human power. From these problems, a technological innovation is needed to help overcome the existing problems. Advances and developments in IoT technology can facilitate various kinds of work, including controlling hydroponic systems, so that plant care can be carried out remotely and at any time. Information system is a technology that can be used as remote plant monitoring. Information will be obtained through monitoring devices that will be sent to the information system. The method used in this research activity is linear regression method. This method can determine the nutritional valve opening the next day, so that nutrition can be monitored using the system
Klasifikasi Kebakaran Hutan Menggunakan Metode K-Nearest Neighbor : Studi Kasus Hutan Provinsi Kalimantan Barat
No full textA very wide forest could cause natural disaster such as forest fire that resulting losses to inhabitant, one of which effecting health and safety. West Kalimantan province is one of the province in Indonesia that has wide area of forest with 8,200,000 ha of forest and 1,600,000 ha of peatland all over the Kalimantan Island. Therefor this study is focusing on the data of west Kalimantan province forest. The aim of the study is to classify forest fire in West Kalimantan Province and followed by designing a REST API application of forest fire detector. In hope that in future, the application will be useful to prevent forest fire in the area of west Kalimantan Province. K-Nearest Neighbor method and balltree algorithm are used in this study to collect and process the data. The sample that are collected about 30% of 14,201 data with accuracy up to 92% with K = 18
Optimasi Neural Network Dengan Menggunakan Algoritma Genetika Untuk Prediksi Jumlah Kunjungan Wisatawan
No full textWest Nusa Tenggara is one of the tourist attractions in Indonesia which has a certain attraction for tourists. With the increase in tourism in NTB, it is necessary to make adequate efforts to maintain tourist objects and attractions. In an effort to maintain a tourist attraction, the NTB provincial tourism office needs to analyze and predict the arrival of local and international tourists. The current analysis and prediction process is still being carried out by collecting data from each tourist attraction entrance. The processed data produces predictions of tourist arrivals, both local and international, where the data processing process takes a long time and requires high human resources. To overcome these problems, it is done by applying computational predictions. Computational predictions can minimize the prediction time and human resources required. The method used is a neural network algorithm with optimized parameters using a genetic algorithm. The optimized parameters are the hidden layer, the number of neurons in the input layer, momentum and others. The data used is time series data from 1997 to 2018. From the neural network experiment, the parameters of the number of neurons in the input layer xt-7 are determined, the number of neurons in the hidden layer 10, the training cycle value is 400, the learning rate value is 0.3 and the momentum value is 0.2. From the experiment, the RMSE value of 0.050 was obtained. While the RMSE value for the neural network algorithm parameters optimized using the genetic algorithm is 0.044. Because of this, it can be stated genetic algorithm with neural network can be used to determine the hidden layer and the number of hidden nodes, the right features, momentum, initialize, and optimize the weight of the neural network. So that the application of the genetic algorithm to optimize the parameter values of the neural network algorithm is better than the application of the neural network algorithm without optimization
Aplikasi Pedagang Sayur Untuk Daftar Harga Bahan Pangan Subsistem Aplikasi Android Untuk Pedagang
No full textAbstract: All economic operations disturbed by technological centers or traditional markets during the Covid-19 epidemic will benefit from the development of this information or information system capable of supporting business activities in every line of life. A vegetable trader\u27s work entails selling items such as vegetables, meat, fish, and other items that are frequently sought after by the community to meet their daily dietary requirements. Traders have significant challenges due to the limited number of market visitors and the rapid decay of merchandise. The goal of this research is to create a mobile veggie application utilizing the React Native framework and the Waterfall approach to design Android-based applications that are simple to use. Customers can order via Whatsapp since it is simpler and easier to follow up, and the majority of customers must be familiar with Whatsapp. Customers can examine prices, types/categories, and place orders via the app, which is an android-based application.
Keywords: Vegetable seller; Android; Waterfall
Abstrak: Berkembangnya teknologi informasi atau sistem informasi saat ini telah mampu mendukung kegiatan bisnis pada setiap lini kehidupan hal tersebut menjadi faktor pembantu saat segala proses ekonomi terganggu oleh pembatasan kerumunan pada pusat perbelanjaan atau pasar tradisional selama masa pandemi Covid-19. Pedagang sayur adalah sebuah pekerjaan yang menjual barang dagangan seperti sayuran, daging, ikan, dan lain-lain yang dagangannya seringkali dicari oleh masyarakat untuk memenuhi kebutuhan bahan pangan sehari – hari. Rendahnya jumlah pengunjung pasar dan cepat membusuknya bahan dagangan menjadi masalah besar bagi pedagang. Tujuan dari penelitian ini adalah membangun suatu aplikasi sayur mobile menggunakan framework React Native untuk mengembangkan aplikasi berbasis Android dengan menggunakan metode Waterfall, sehingga aplikasi yang dibangun mudah digunakan. Hasil dari penelitian ini adalah aplikasi berbasis android untuk memudahkan pedagang menambahkan data dagangan karena mayoritas sudah memiliki hp android, pelanggan bisa memesan melalui Whatsupp karena lebih simple dan mudah di follow up, mayoritas pelanggan pasti sudah familiar dengan Whatsupp, Customer bisa melihat harga, jenis/kategori melakukan pesanan via app.
Kata kunci: Pedagang Sayur; Android; Waterfall
The Customer Profiling berdasarkan Model RFM dengan Metode K-Means pada Institusi Pendidikan untuk menunjang Strategi Bisnis di Masa Pandemi Covid-19
No full textIdealnya sebuah perguruan tinggi harus bisa beradaptasi untuk tetap membuat bisnisnya bertahan dan berkelanjutan dalam situasi apapun, seperti pandemi saat ini yang berdampak pada berbagai sektor termasuk sektor pendidikan seperti perguruan tinggi X di Denpasar, Bali. Berdasarkan data pada bagian pemasaran di perguruan tinggi X, terdapat penurunan jumlah penerimaan mahasiswa baru jika dibandingkan saat kondisi normal dengan saat pandemi berlangsung serta belum teridentifikasinya profil kelompok pelanggan potensial di perguruan tinggi tersebut. Solusi yang dapat dilakukan adalah melakukan identifikasi karakteristik pelanggan potensial / customer profiling pada perguruan tinggi X sehingga dapat diketahui kelompok pelanggan potensial pada perguruan tinggi X. Customer profiling dilakukan dengan Model RFM (Recency, Frequency, Monetary) dan metode data mining, yaitu K-Means terhadap data transaksi mahasiswa selama tahun 2019 - 2020. Penelitian ini bertujuan untuk mengidentifikasi profil karakteristik pelanggan yang ada pada perguruan tinggi X dan mendapatkan rekomendasi strategi pemasaran di masa mendatang berdasarkan hasil profiling tersebut. Berdasarkan hasil analisis didapatkan karakteristik dari empat (4) kelompok profil pelanggan pada Perguruan Tinggi X, yaitu “Sangat Potensial”, “Potensial”, “Netral” dan “Tidak Potensial”. Kemudian didapatkan juga rekomendasi strategi pemasaran yaitu strategi retensi untuk kelompok “Sangat Potensial” dan “Potensial”, strategi Up Sell untuk kelompok “Sangat Potensial”, “Potensial” dan “Netral”, strategi Cross Sell untuk kelompok “Sangat Potensial”, “Potensial” dan “Netral” serta strategi promosi untuk seluruh kelompok pelanggan di Perguruan Tinggi X
Implementasi Convolutional Neural Network Untuk Deteksi Emosi Melalui Wajah
No full textThe human emotional condition can be reflected in speech, gestures, and especially facial expressions. The problem that is often faced is that humans tend to be subjective in assessing people\u27s emotions. Humans can easily guess someone\u27s emotions through the expressions shown, as well as computers. Computers can think like humans if they are given an algorithm for human thinking or artificial intelligence. This research will be an interaction between humans and computers in analyzing human expressions. This research was conducted to prove whether the implementation of CNN (Convolutional Neural Network) can be used in detecting human emotions or not. The material needed to conduct facial recognition research is a dataset in images of various kinds of human expressions. Based on the dataset that has been obtained, the images that have been collected are divided into two parts, namely training data and test data, where each training data and test data has seven different emotion subfolders. Each category of images is 35 thousand data which will later be trimmed to around a few thousand data to balance the dataset. According to their class, these various expressions will be classified into several emotions: angry emotions, happy emotions, fearful emotions, disgusting emotions, surprising emotions, neutral emotions, and sad emotions. The results showed that from the calculation of 40 epochs, 81.92% was obtained for training and 81.69% for testing
Sistem Monitoring berbasis Desktop untuk Perangkat Mini Exhausting Pada Proses Pengalengan Ikan
No full textOne of the potential marine resources that can develop the economy is fisheries. Fishery potential in Indonesia is estimated at 7.3 million tons per year. However, the community has only utilized the empowerment of fish potential so far, only 80%. Therefore we need a processing business that can extend the shelf life while increasing the added value of fishery products. One of the processing processes that can preserve longevity is the canning process. Canning can be interpreted as processing using a sterilization temperature that aims to save the food material from the spoilage process. In a previous study, mini exhausting equipment was developed to produce fish in cans with a capacity of 200 115mL cans. A temperature monitoring system is needed during the exhausting process to ensure quality. Therefore, in this study, a desktop application-based monitoring system was created to display and store temperature data during the exhausting process
Rancang Bangun Sistem Informasi Pengarsipan dan Pendistribusian Surat
No full textArchive management is very important for an institution. Archive management at Panca Marga University has not been done computerized. Manual management raises several problems, including slow search, need for extensive mail storage and rather slow distribution. These problems can be solved by building an information system for filing and distributing mail. System development use the waterfall method. In this study, a system can be built to be able to manage incoming letters, outgoing letters, decision letters, letter dispositions along with the distribution of the letters. Based on the results of black box testing, the system that was built was running according to its functionality