<p>Indonesia merupakan salah satu negara dengan keanekaragaman tanaman buah tropika yang cukup tinggi. Keanekaragaman tanaman buah tropika tersebut merupakan satu tantangan dalam melakukan identifikasi. Identifikasi tanaman dapat dilakukan berdasarkan buah, bunga, maupun daun. Identifikasi berdasarkan daun merupakan identifikasi yang lebih mudah dilakukan karena daun akan ada sepanjang masa, sedangkan bunga dan buah mungkin hanya ada pada waktu tertentu. Identifikasi tanaman menggunakan daun dapat dilakukan berdasarkan bentuk, tekstur, maupun warna citra daun tersebut. Pada penelitian ini, ekstraksi fitur gray level co-occurrence matrix (GLCM) dari tekstur citra permukaan daun buah tropika digunakan sebagai input dari pelatihan Jaringan syaraf tiruan untuk proses identifikasi. Secara keseluruhan, pengujian dengan menggunakan hidden neuron sebanyak 7 menghasilkan hasil akurasi terbaik, yaitu 90%.</p><p>Kata kunci: buah tropika, daun, GLCM, jaringan syaraf tiruan, tekstur.</p>

The pairwise alignment (PA)

Planting seeds may be trivial and can be done manually. However, on a large scale, it will inevitably become time-consuming and labor intensive. The use of robot can be an alternative solution to improve the efficiency of this agricultural-related work so that farmers can focus more on the decision making perspective rather than the labor-intensive works. This study aims to develop a prototype of a task-oriented seed-planter robot that can be used to assist farmers. The robot has three wheels: two motorized wheels and one free-wheel for its stability. It is equipped and programmed with line follower sensors and algorithm to simplify its navigation procedure, by assuming that the field is already marked before plantation process. The main contribution of this study is the design of the actuators of the robot prototype which enables the robot prototype to dig a hole, plant the seed and then close the hole again.

Purpose: A remote visual monitoring system will be very helpful for chicken farmers to monitor their cages, that usually located away from their houses. This system needs adequate bandwidth in transmitting the video over the internet, which is usually very limited in urban areas. The main goal of this research is to develop an automatic chicken coop remote monitoring system and define the optimum video resolution to be transmitted. Methods: We used an 8 MP Raspberry Pi camera V2 to record the video and send the results to Google Drive by utilizing the GDrive API. Furthermore, a live streaming video from the chicken coop is accessible through a simple HTTP web page utilizing ngrok as a tunneling software so that the live streaming video can be publicly accessed from anywhere using a web browser. Three video resolutions of 640x480, 800x600, 1024x768 with 15 and 30 framerates were used in our experiments. Each scenario has a duration of five minutes and takes 12 times.Result: The experiment results showed, resolutions that provide a stable video recording and streaming are 640x480 and 800x600. The resulting system succeeded in performing live streaming along with the process of data acquisition. Value: The Google Drive infrastructure is used because of its popularity and convenience by people with limited digital literacy such as smallholder chicken farmers. Furthermore, the video produced by this system can be used in supporting research of chicken behavior pattern identification to build a system notification of an emergency situation in the cage.

No abstract