SISTEM IDENTIFKASI PENYAKIT TANAMAN CABAI MENGGUNAKAN METODE SIMPLE ADDITIVE WEIGHTING (SAW) BERBASIS ANDROID

Chili is an important commodity in Indoneisa’s economy. The fluctuating price causes chili to contribute to inflation for national economy. Chili’s price could increase because of demand in high level and production of chili in low level. The emergence of disease causes production of chili decreas. To solve the problem in chili disease, the disease needs to be diagnose as soon as possible. To diagnose the disease as soon as possible there is a need of chili expert system using android. Chili’s disease will be indentificated by inputting the symptoms which are shown by the plan. Expert system of chili plant disease identification design is based Android. Android Mobile is used as a device to insert the symptoms which are shown by the plant. The system will manage the symptoms that have been selected and show the diagnoses of the disease and how to control the disease. This system was designed using the Simple Additive Weighting (SAW) method and tested using Blackbox method. Testing using Blackbox method to show the system is able to identify the diseases of chili plant

PENGEMBANGAN SISTEM INFORMASI GEOGRAFIS PELAPORAN KERUSAKAN DAN KEGIATAN PENINGKATAN RUAS JALAN DI KOTA BANDAR LAMPUNG

Roads are one of the factors that support the development of the region as a whole. Management of reporting of damaged roads at Bandar Lampung Public Works Agency still uses paper documents and the dissemination of road information to the community is not good enough. Therefore, in this study a geographic information system (GIS) will be developed as an innovation to simplify the process of reporting damaged roads to be more efficient and to better disseminate information to the public. GIS is a system designed to work with data that is spatially referenced or geographic coordinates. The design of this system uses Use Case, Activity Diagram, Sequence Diagram, and Class Diagram. The system implementation uses Google Maps API and is developed using PHP and Javascript programming languages and MySQL database. Based on the results of the analysis of system testing, the average value of the overall test obtained was 3,78. Which is looked Based on interval table of the Likert scale, the final value of test shows that GIS was successful. The results of the black box test also show that each function in each menu on the system has been running according to the procedure.

Sistem Pakar Diagnosa Penyakit Tanaman Kopi Menggunakan Metode Dempster Shafer

At present the total area of Indonesian coffee plantations is ranked second in the world, but for the production and export of Indonesian coffee there is at number four in the world. The low productivity of coffee is caused by inadequate crop cultivation techniques, this encouraging various plant growth disorders. Based on the problems, coffee farmers need a tool that can provide information about coffee plants and diseases that attack coffee plants and provide solutions to handle these diseases. One branch of computer science that can help is the expert system (Expert System). Expert systems use the knowledge of an expert which is intended to increase knowledge into computers. This research used Dempster-Shafer method to diagnose and to knowing the degree of accuracy of the diagnoses results. Information system and expert system of coffee plants diagnose contains information about plants management that begins from planting until harvest. This system built based on the web, with this system is expected to help provide solutions to handle the coffee plants that have disease, that many coffee plants can be saved from disease and can increase the productivity of coffee plants.

SISTEM PENDETEKSI PENULISAN KATA PADA DOKUMEN BERBASIS WEB

The process of detecting writing errors manually takes a lot of time and requires a source of reference to prove the truth of writing words. The efficiency of time required if done manually certainly will not be optimal, so we need a word writing error detection utility that is expected to make it easier to check errors in a document of type word (.docx). In the process of developing this utility through several stages of the process, namely Cleansing, Case Folding, Tokenization, Stemming and Dictionary Lookuup. The result of the docx document being processed is influenced by the completeness of the dictionary used as a reference for word correction and the type of word spelling errors

PENGEMBANGAN SISTEM ADMINISTRASI PEMBAYARAN SUMBANGAN PEMBINAAN PENDIDIKAN (SPP) SEKOLAH MENENGAH ATAS BERBASIS WEB

School is a level and continuous education unit for organizing teaching and learning activities. The system of financial administration of students at schools such as SPP (tuition) payments is one example of administration system that most of the data writing still use manual system. Writing data using a manual system sometimes has errors (human error) and data loss, this is because the writing and storage is done as well and less precision when entering data. Developing a Web-based school's financial administration information system using the Laravel Framework resolves these issues. In this study, system development used the PHP programming language and the Laravel Framework. Functional testing System using Black Box testing with Equivalence Partitioning (EP) method. The result of the developed system provides the school's ease of logging the student SPP (tuition) payment.

Signature Identification Menggunakan Metode Template Matching dan Fuzzy K-Nearest Neighbor

— Signature is the result of the process of writing a person of a particular nature as a symbolic substance, which means a symbol or mark. Signature is usually used as an identifying mark of a person, each person must have his own signature in a different pattern. Because it's used as a person's identifying badge, Signatures now become particularly susceptible to counterfeiting and abuse that require check with a signature pattern recognition. This research has created a signature pattern recognition system using methods Template Matching and Fuzzy K-Nearest Neighbor to help recognize a person's signature pattern. The number of signatures used is 110 in two categories: the original signature with 100 data and the false signature with 10 data, and there were 10 classes taken using smartphone cameras. From this research, it was found that the best value from the image size of 200x200 pixels was 92% of the class that owned the signature legible, Positive Predictive Value (PPV) 88% and False Rejection Rate (FRR) 12%, with a k=3 on the original signature, and 90% of the class that owned the signature legible, Negative Predictive Value (NPV) 90% dan False Acceptance Rate (FAR) 10% with a k=9 on the false signature. From these results, it could be concluded that methods Template Matching and Fuzzy K-Nearest Neighbor could be used for signature pattern recognition.

STUDI MOBILE COMMERCE DI BANDAR LAMPUNG

The online shopping process in Bandar Lampung is facilitating by mobile commerce online shopping. The factor of using online shopping mobile commerce has never been analyzed based on the public perception in Bandar Lampung. This research discusses using mobile-commerce online shopping using the UTAUT2 model with Perceived Risk manifestations, namely Security Risk and Privacy Risk. The mobile commerce applications analyzed were Shopee, Lazada, Tokopedia, Bukalapak, and Blibli. The purpose of this research was to determine the UTAUT2 variable with the manifestation of Perceived Risk, namely Security Risk and Privacy Risk, which affect the use of online shopping mobile commerce. The data analysis method used is Structural Equation Modeling (SEM) with Partial Least Square (PLS) approach. The total number of respondents obtained was 183 respondents. The data tested were 373 data. This research results from the factors that most influence the behavioral intention and use behavior of mobile commerce online shopping is a habit.

APLIKASI PERMAINAN SEBAGAI MEDIA PEMBELAJARAN PETA DAN BUDAYA SUMATERA UNTUK SISWA SEKOLAH DASAR

Indonesia secara umum mempunyai banyak keanekaragaman budaya dari berbagai pulau. Pulau Sumatera termasuk dalam pulau-pulau terbesar di Indonesia. Seiring dengan perkembangan zaman, kebudayaan yang ada di Indonesia pada saat ini secara perlahan mulai terlupakan. Oleh karena itu tujuan dari penelitian ini adalah memberikan alternatif lain untuk mengenalkan pulau Sumatera pada pelajar sekolah dasar melalui aplikasi permainan sehingga siswa tidak mudah bosan dan tertarik untuk mengetahui sejarah masing-masing provinsi, rumah adat dan pakaian adatnya. Penelitian ini dikembangkan dengan menggunakan construct 2 dan metode pengembangan Multimedia Development Life Cycle. Hasil penelitian ini berupa aplikasi permainan pengenalan peta dan budaya Sumatera yang dapat dijalankan melalui smartphone berbasis android dengan disertakan latihan soal, untuk mengetahui sejauh mana kemampuan siswa mendalami materi yang didapat dari game ini. Aplikasi ini telah diuji kepada siswa sekolah dasar dengan rata-rata hasil 94% atau sangat baik.

KLASIFIKASI TANAMAN JARAK PAGAR MENGGUNAKAN ALGORITME DEEP LEARNING H2O

Tanaman jarak pagar merupakan tanaman multi fungsi yang memiliki banyak manfaat dari daun hingga buah. Tanaman jarak pagar sering digunakan untuk produk kecantikan hingga pengganti biodiesel. Penyakit yang menyerang tanaman jarak pagar dapat mengganggu hasil dari tanaman jarak pagar. Kurangnya pakar dibidang ini dan pengetahuan yang dimiliki petani menyebabkan sesuatu yang buruk. Persoalan ini dapat diselesaikan dengan metode Deep Learning. Metode Deep Learning yang digunakan adalah H2O. H2O digunakan karena dapat memberikan hasil komputasi yang cepat dan bisa memberikan akurasi yang baik. Pada penelitian ini bisa kita lihat bahwa H2O memberikan akurasi rata-rata maksimal sebesar 96,066% dengan parameter uji kombinasi data latih dan data uji 60:40, menggunakan satu layer dan jumlah epoch sebanyak 100. Pada penelitian ini membuktikan bahwa H2O bisa digunakan untuk identifikasi penyakit tanaman jarak pagar

PENGGABUNGAN DUA KONEKSI INTERNET SERVICE PROVIDER DENGAN TEKNIK LOAD BALANCING MENGGUNAKAN METODE EQUAL COST MULTI PATH

Computer networks turn out to be one of the primary needs in life in this era of the globalization. Computer networks are often used simultaneously at certain times so that it can cause overload of bandwidth on the computer network. Overloaded bandwidth can cause disturbances such as networks that feel slower than usual. This study discusses the merger of two service provider internet connections that is done by load balancing techniques using the equal cost multipath method. The stages that will be carried out are analysis, design, simulation or prototyping, implementation, monitoring, and management. The results of the implementation of the application of load balancing techniques with the equal cost multipath method get an increase in the QoS value which can be seen from the test parameters performed namely the average throughput on all computers has increased 0.17%, the average delay for all computers has a decrease in quality of 0.9 milliseconds, the average jitter of all computers has increased the quality of 0.68 milliseconds, and the average packet loss in all computers experienced a 0.58% quality improvement. The configuration of this study was made easier with the help of the web configuration made.