(1) Background: The management of forest and land fires has become of concern to the Indonesian government, as demonstrated by the issuing of the Presidential Instruction of the Republic of Indonesia Number 11 of 2015, then replaced by Number 3 of 2020, concerning Forest and Land Fire Management. In 2002, the Ministry of Environment and Forestry (MoEF) established Manggala Agni, a forest fire management organization, at the central government level. This study aims to explain the development of the Indonesian Forest and Land Fire Prevention Patrol System. The system development was conducted by the Computer Science Department of IPB University, in collaboration with the Agency for Climate Change and Forest and Land Fire Management, as well as the Directorate of Forest and Land Fire Management, MoEF. (2) Methods: The system development adopted the steps in the prototyping method, namely communication, quick planning, rapid design modeling, and prototype construction, as well as dissemination, submission, and feedback. (3) Results: The web-based system for the real-time monitoring and analysis of the forest and land fire prevention patrol is integrated into a mobile application for recording field observations during patrol activities. The system testing was successfully conducted by involving the users. The test results show that all features in the system are working correctly and meet the user’s requirements. The mobile application has saved 36.02% of the time for recording the patrol data and 40.32% for creating the patrol reports. In addition, using the web-based application has saved time in preparing the patrol reports by 56.48%.

Hermadi I, Wulandari, Dhira D. 2022. Development of a protected birds identification system using a convolutional neural network. Biodiversitas 23: 2561-2569. The protected animals are the animals having small populations, a sharp decline in the number of individuals in the wild, or endemic. The government has banned owning, keeping, or trading these animals. The first step in conserving these animals is identification. The government of the Republic of Indonesia has defined 564 species of bird as protected. This issue becomes a challenge to bird species identification. This study aims to develop a web application that implements a convolutional neural network (CNN) model for image-based protected bird species identification. This study uses the images of ten protected bird species in Indonesia as the research subject. This study consists of the stages viz. data collection, data preprocessing, data splitting, CNN model development, model evaluation, and web development using the Prototyping method. This study has successfully developed a model that gained 97% accuracy, 98% precision, and 97% recall on testing data. The study utilized HTML, CSS, Javascript, and Tensorflow.js for Web development. The black-box testing result shows that the prototype is acceptable.

This paper considers the problem of task allocation where the goal is to find a coalition of UAVs (agents) to complete on-farm agricultural tasks. In this study, Ant Colony Optimization (ACO) algorithm is employed to find the best coalition of agents. The performance of the basic ACO algorithm for solving task allocation is improved by modifying the efficiency factor. In the proposed algorithm, the efficiency factor is defined as a function that relates not only to the capability of the agents and the distance between the agents, but also to the distance between the agents and the target. To solve the task allocation problem, the capability list of the agents was also adjusted using common UAV capabilities in agricultural application. Simulation results showed that the proposed ACO algorithm with the modified efficiency factor improved the performance of basic ACO algorithm for solving task allocation problem in terms of the average total travel cost for each agent. The optimum number of ants and agents in the proposed algorithm was also analysed for robust performance. Simulation results revealed that the addition of the numbers of agents and ants increases the average efficiency of the algorithm. In this study, we have also added a function to calculate the system capability utilization. By employing such a function, simulation results show that the total resource used by the agents and total communication cost can be optimized. In addition, a simple experiment using five ground robots with a centralized control was also carried out as a proof of concept for the proposed algorithm.

The high market demand for broiler chickens requires that chicken farmers improve their production performance. Production cost and poultry welfare are important competitiveness aspects in the poultry industry. To optimize these aspects, chicken behavior such as feeding and aggression needs to be observed continuously. However, this is not practically done entirely by humans. Implementation of precision live stock farming with deep learning can provide continuous, real-time and automated decisions. In this study, the you only look once version 4 (YOLOv4) architecture is used to detect feeding and aggressive chicken behavior. The data used includes 1,045 feeding bounding boxes and 753 aggressive bounding boxes. The model training is performed using the k-fold cross validation method. The best mean average precision (mAP) values obtained were 99.98% for eating behavior and 99.4% for aggressive behavior.

Sampah masih menjadi salah satu masalah yang sulit untuk ditangani oleh pemerintah Kota Bogor. Dengan jumlah penduduk mencapai angka 1.08 juta jiwa, jumlah sampah yang dihasilkan perharinya mencapai 2 532.5 liter. Jumlah sampah yang tergolong banyak ini hanya diakomodasi oleh jumlah armada angkutan sampah yang terbatas. Hal ini mengakibatkan sampah di Tempat Penampungan Sementara (TPS) menumpuk sehingga mencemari lingkungan. Oleh karena itu, diperlukan sebuah sistem monitoring jarak jauh untuk mengetahui volume timbulan sampah. Penelitian ini membangun sebuah prototype untuk mengetahui volume timbulan sampah secara real-time dan memberikan notifikasi untuk pengambilan sampah di luar jadwal regular, yaitu ketika volume timbulan sampah mendekati volume maksimal bak sampah. Metode yang digunakan dalam penelitian adalah frame difference algorithm dan perspective transformation. Selain itu, penelitian ini juga menerapkan konsep Internet of Things dalam aplikasi berbasis mobile sebagai sistem monitoring dan notifikasi. Nilai error atau RMSE antara tinggi aktual volume timbulan sampah dan tinggi timbulan volume sampah hasil pengolahan citra yang didapat adalah 0.2060 dan akurasi sebesar 97.93 persen.