Coffee has been cultivated as the secondary produce for decades in Girimarto, Wonogiri, however, the selective picking practice remain alient for local farmers. Selective picking is considered impractical due to time consumption and laborous work that farmers should carry out. The community service project designs and implements image recognition technology to help acquire coffee-cheery ripeness condition. Adopting a geolocation, the appropriate routing strategies, would enable farmers to selectively pick the red cherries in a systematic sequence. The image processing technology was applied by adopting Raspberry Pi microcomputer, Raspberry Pi Camera Board, version 2, and OpenCV programming language. The transition to selective picking and the subsequent post-harvest technology would likely produce high-quality green bean coffee. It is expected that the income of smallholder coffee farmers will gradually be increasing.
Implementasi perubahan Kurikulum Tingkat Satuan Pendidikan (KTSP) ke Kurikulum 2013 berdampak pada sistem penilaian siswa. Penilaian pada Kurikulum 2013 terdiri dari beberapa komponen, yaitu komponen sikap, pengetahuan dan ketrampilan. Pada saat penelitian dilakukan, pencetakan laporan studi atau rapor di Sekolah Dasar dilakukan dengan cara manual, sehingga membutuhkan waktu yang lama dan tidak efisien. Penelitian ini bertujuan untuk membuat Sistem Informasi Pengolah Nilai untuk Kurikulum 2013 yang diimplementasikan untuk Sekolah Dasar. Metode penelitian yang digunakan adalah Model Research and Development (R&D). Sedangkan model pengembangan aplikasi menggunakan Model Waterfall. Kelayakan sistem diuji berdasarkan standar ISO 9126. Aspek yang digunakan yaitu antara lain functionality, usability, maintainability, dan portability. Pengujian tingkat kelayakan sistem informasi dilakukan oleh ahli sistem, ahli substansi, dan pengguna sistem. Pengguna dari sistem ini adalah Guru Mata Pelajaran, Guru Kelas dan Wakil Kepala Sekolah bidang Kurikulum. Hasil pengujian aspek functionality menghasilkan nilai 89,22%, aspek usability menghasilkan nilai 88,75%, aspek maintainability menghasilkan nilai 90%, dan untuk aspek portability menghasilkan nilai 81,66%.
Proses pembelajaran mata kuliah Jaringan Komputer di prodi Pendidikan Teknik Informatika (PTIK), Fakultas Keguruan dan Ilmu Pendidikan (FKIP), Universitas Sebelas Maret (UNS) terjadi sebuah gap antara Mahasiswa dari SMA dan SMK. Sebagian mahasiswa dengan latar belakang SMA belum memiliki konsep-konsep dasar Jaringan Komputer, sedangkan mahasiswa dari SMK sudah pada tahap sudah jauh lebih advance. Untuk menjembatani hal tersebut maka salah satu solusi yang bisa diimplementasikan adalah sebuah e-learning yang menyediakan sistem pembelajaran mandiri. E-learning yang dikembangkan akan menyediakan materi yang lengkap, latihan dan dan video tutorial. Pada penelitian ini, berbeda dengan E-Learning konvensional yang bersifat sama (flat) untuk setiap pengguna, E-Learning yang akan dikembangkan dilengkapi dengan Machine Learning metode Naïve bayes. Machine Learning akan membantu proses pembelajaran dengan pendekatan one-to-one, dimana sistem akan memiliki kemampuan mendeteksi kemampuan mahasiswa yang menggunakan E-Learning. Sistem menyesuaikan materi dan latihan sesuai dengan kemampuan pengguna dalam proses belajar mandiri. Dengan tutorial yang bertahap dan pendekatan yang berbeda dalam proses belajar setiap siswa diharapkan mampu meningkatkan pemahaman siswa mengenai mata kuliah Jaringan Komputer di PTIK, FKIP, UNS.
Based on observation in class X TKJ SMK Negeri 1 Sawit. Students had some problem when learning computer assembly. That happens because lack of equipment and learning media. They need a learning media that can be used to study computer assembly not only inside a school but outside as well. We propose to solve that problem with developing a new learning media that can help students learn independently. We develop a module and android based augmented reality application called ARRAKOM . when ARRAKOM detect a marker in the module. It can display a 3-dimensional model in real time. Learning media is created using ADDIE consist of Analysis, Design, Development, Implementation, and Evaluation. In the development stage, we are using an incremental model and created 2 prototypes of ARRAKOM. In result of the feasibility test, Arrakom gets measured with a Likert scale from expert media get percentage 75% very good, 25% good, 0% bad, 0% very bad. for expert material get percentage 57% very good, 43% good, 0% bad, 0% very bad. And from user get percentage 47% very good, 43% good, 3% bad and 0% very bad.
This research provided device management automation for computer laboratories using Arduino. Some devices in computer laboratories such as Air Conditioners and LCD Projectors were always on while the device not used. It caused inefficient uses of electricity resulting in increased electricity bills and reduce the device lifetime. Device automation made the electronic devices work automatically. The first automation we applied on the Air Conditioner, the other one was on LCD Projectors. This schematic developed based on Arduino Uno R3 with several components such as the infrared transmitter, humidity sensor DHT11, relay board and I2C OLED display. Arduino Uno R3 provided as the central controller. The two methods of testing were used for measuring this system performance. The first test was done by testing the performance of the components used, such as the IR Transmitter, DHT11, relay board, and I2C OLED Display. The second test was done by testing the functionality of Arduino Uno R3 as a controller. This test resulted that the automation system can work properly with fully automatic control LCD projectors and air conditioners by periodically stabilizing room temperature and turning on the projector’s LCD automatically when needed.
Indonesia is a country with rapid technological developments in all sectors including education. This can be proved by the government’s success in applying computer-based test in 2014 junior high school. Many conveniences obtained when the exam using computer such as the assessment automatically, get feedback quickly and the question can be stored in the bank question. In this research, computer-based test system will be developed based on the convenience as above and will be added some other features to suit of the school using waterfall development model. Additional features include classroom major, question grouping in the question bank, user management and ease of registration during new year academic calendar. After developing system has been done, the CBT system is tested to one class at a vocational high school in Indonesia using an system feasibility instrument adapted from technology acceptance model (TAM) to know the level of feasibility the CBT system in perceived usefulness and perceived easy of use. The test results show that CBT system is very suitable for use in the class and can be applied to all schools in Indonesia.
Bursa Kerja Khusus (BKK) di Sekolah Menengah Kejuruan berguna untuk menyebarkan informasi lowongan pekerjaan bagi siswa/alumni SMK. Sistem ini bermanfaat menyebarkan informasi. Namun dengan banyaknya lowongan maka siswa diharuskan memilih perusahaan-perusahaan yang sesuai dengan minat dan keahliannnya. Untuk mengatasi masalah tersebut, pada penelitian ini akan dilakuan penggembangan sistem rekomendasi bagi Bursa Kerja Khusus (BKK). Selain membantu penyebaran informasi, sistem dilengkapi dengan fitur rekomendasi. Siswa/alumni calon pencari kerja akan mendapatkan rekomendasi mengenai perusahaan yang sesuai dengan minat dan keahliannya. Sedangkan bagi perusaan akan diberikan rekomendasi calon pendaftar yang memiliki keahlian yang dibutuhkan oleh perusahaan. Sistem rekomendasi menggunakan metode pengambilan keputusan Simple Additive Weighting. Metode Simple Additive Weighting memberikan bobot terhadap setiap atribut yang kemudian dilanjutkan dengan adanya proses perangkingan semua atribut. Penelitian dan pengembangan ini menggunakan metode penelitian Research and Development (R&D) oleh Borg and Gall. Pada penilaian oleh ahli sistem menunjukkan hasil 88.9%. Penilaian dari dua ahli substansi menunjukkan hasil 87.8%. penilaian dari siswa/ alumni SMK menunjukkan hasil 88.3%. Sedangkan penilaian dari perusahaan menunjukkan hasil 92.1%. Keseluruhan penilain tersebut berada pada rentang 81% – 100%, sehingga sistem dikategorikan sangat layak untuk digunakan.
Penelitian mengenai pengenalan karakter plat nomor kendaraan atau Automatic License Plate Detection (ALPR) sudah banyak dilakukan. Berbagai metode machine learning digunakan pada proses pengenalan karakter plat nomor kendaraan. Pada penelitian ini akan membandingkan metode K-Nearest Neighbor (KNN) dan Support Vector Machine (SVM) dalam pengenalan karakter plat nomor kendaraan. Pengujian sistem pada 20 pengujian didapatkan hasil sebagai berikut: Akurasi pengujian pengenalan plat kendaraan dengan metode Support Vector Machine dengan akurasi 95%. Sedangkan menggunakan metode KNN mendapatkan akurasi pengujian 80%.
Technological advances can be utilized to make information dissemination faster and more efficient. One example of the use of technology as a medium of information and management in the implementation of the conference is an information management system based on WEB. Based on the observations that have been conducted, found various problems, among others for the preparation of activity data reports, data participants, and so forth, actually already utilizing information technology, but still less effective. So many weaknesses that appear like; less effective and efficient in data processing, the time required for the preparation of reports long enough and the risk of error becomes large. Then from the side of presence also still printed manually. In addition, all the participants who register will be placed certificates, although the participants are not present in the conference, this happens because of the organizers difficult to sort out which participants are present and not present. In this article presented the feasibility test results of the conference management information system developed. Testing is performed on system experts, substance experts, and users. Expert testing system using the instrument referring to ISO 9126 get 93% percentage. Expert testing of substance using instrument referring to ISO 9126 get 86% percentage. While testing of users using the instruments that refer to ISO 9126 aspects of functionality gets an average percentage of 88.2%.
The Automatic License Plate Recognition (ALPR) has been becoming a new trend in transportation systems automation. The extraction of vehicle’s license plate can be done without human intervention. Despite such technology has been widely adopted in developed countries, developing countries remain a far-cry from implementing the sophisticated image and video recognition for some reasons. This paper discusses the challenges and possibilities of implementing Automatic License Plate Recognition within Indonesia’s circumstances. Previous knowledge suggested in the literature, and state of the art of the automatic recognition technology is amassed for consideration in future research and practice.
Historical learning in Indonesia is very minimal innovation. Due to the lack of innovation from year to year emerged various problems in historical learning activities such as monotonous, boring and uninteresting. The variety of learning media will be able to increase interest of learners in the learning process. The result of this research is an interesting and non-boring Android-based history learning media that is called Sekar Indonesia and worthy of being used as a learning media. This research method is research and development (R & D). This study was conducted using a research model developed by Borg & Gall. The research model consists of five steps: research and data collection, planning, product drafting, preliminary field testing and main product revision. Applications Sekar Indonesia tested by material experts, media experts and users. Expert testing results obtained percentage of 86.1% from material experts, 92.85% from media experts, and 97.7% form users. From the test results obtained the conclusion that the application Sekar Indonesia that has been developed can be used as a learning media.
The activities of the job training is an activity that must be implemented at Vocational Secondary School. The lack of utilization of technology on such activities in Vocational Secondary School, so the data management of the job training become less effective and efficient. Therefore, it is necessary the information system for manage the data on the job training and produces the decision support of the decent industry of the job training as a result of the evaluation of the job training. This research has a goal to produce decision support system to determine the feasibility of the job training industry (SPK-KTP), measure the feasibility of the system, and produce a decision support using a Simple Additive Weighting (SAW) method. The information system can help the school to manage the administration on the job training, recap the daily journal, recap the reports in pursuit, and provide decision support the job training of decent industry used in the next period. SPK-KTP uses SAW method to produce decision support the job training of decent industry. SPK-KTP is the web-based information system which it is developed using the programming language PHP (Hypertext Preprocessor). This information system uses The Waterfall Model as its system development method. The steps of The Waterfall Model consists of Analysis, Design, Code, and Test. SPK-KTP has done testing to an expert of the information system with value 90,7%, an expert of the substance of the job training with value 91,6%, supervising teachers with value 83,3%, and learners with value 90,6%. Based on the result, so SPK-KTP is very decent to use.
Research on License plate detection system will be developed in this research. Vehicle plates detection will use a camera that mounted on parking gate. Detection process starts with collecting data using the camera. Preprocessing includes rescale the image into (640.480) pixels, converting the image into grayscale. Smooting process with blur method is used to reduce the image noise. Edge detection using Sobel on the vertical direction and thresholding. Segmentation process will combine 2 methods, Morphology Filter and Connected Component. Support Vector Machine (SVM) is used to test whether the candidate is a plat plate or not. Parking System Testing obtained the following results: Parking System Accuracy in detecting motorcycle plate is 78% and the accuracy car plate detection is 78%
The aim of this research is to distinguish the authenticity of paper notes using detection system based on algorithm of Linear Vector Quantization (LVQ) Neural Network. The object image “dancer” of the paper currency Rp. 50.000.00 fluorescent by ultraviolet light used as the input for the system. The coding was built using visual programming language. The size of the feature of the dancer tested object is 114×90 pixels and its Red-Green-Blue-Hue-Saturation-Intensity (RGBHSI) values were extracted as the input for LVQ. The experimental result shows that the system can distinguish the authenticity of original paper notes fairly satisfy. It has accuracy up to 100% of detecting 20 real test case data, and 96% of detecting 22 simulated test case data.
This research is aimed to test a paper currency counterfeit detection system based on Linear Vector Quantization (LVQ) Neural Network. The input image of the system is the dancer object image of paper currency Rp. 50.000,- fluorescent by ultraviolet light. The image of paper currency data was taken from conventional banks. The LVQ method is used to recognize whether the paper currency being tested is counterfeit or not. The coding was carried out using visual programming language. The feature size of the dancer tested object is 114×90 px and the RGBHSI was extracted as the input for LVQ. The experimental results show that the system has an accuracy 100% of detecting 20 real test case data, and 96% of detecting 22 simulated test case data. The simulated case data was generated by varying the brightness of the image data. The real test case data contains of 10 counterfeit paper currency and 10 original paper currency. The simulated case data contains of 11 original paper currency and 11 counterfeit paper currency. The best setting for the system is Learning Rate = 0.01 and MaxEpoh = 10.