As part of the early warning system, forest fire detection has a critical role in detecting fire in a forest area to prevent damage to forest ecosystems. In this case, the speed of the detection process is the most critical factor to support a fast response by the authorities. Thus, this article proposes a new framework for fire detection based on combining color-motion-shape features with machine learning technology. The characteristics of the fire are not only red but also from their irregular shape and movement that tends to be constant at specific locations. These characteristics are represented by color probabilities in the segmentation stage, color histograms in the classification stage, and image moments in the verification stage. A frame-based evaluation and an intersection over union (IoU) ratio was applied to evaluate the proposed framework. Frame-based evaluation measures the performance in detecting fires. In contrast, the IoU ratio measures the performance in localizing the fires. The experiment found that the proposed framework produced 89.97% and 10.03% in the true-positive rate and the false-negative rate, respectively, using the VisiFire dataset. Meanwhile, the proposed method can obtain an average of 21.70 FPS in processing time. These results proved that the proposed method is fast in the detection process and can maintain performance accuracy. Thus, the proposed method is suitable and reliable for integrating into the early warning system.

Fixed-wing UAV has the ability to fly like a plane. For the movement of the flight, a good control system is needed. Part of the flight controls that require our attention among them is the vertical moving control. The controls are used to adjust the vertical movement involving aircraft pitch angle control. To control it, we can use control method that has been commonly used. The control method is a PID (Propositional, Integral and Derivative) control method. PID has three components (Kp, Ki, and Kd). The three components of PID can be obtained in various ways or methods. However, to produce a robust control, a method that can optimize the PID components is needed. Ant Colony Optimization (ACO) is one of PID controller optimization method which adapted by ant colony ability to find the shortest way from their nest to food. Some ACO parameters are a number of ants, parameters, and pheromone component for pheromone. Pheromones are the values given by the ants when they use the road.

The research topic of VTOL (vertical take-off and landing) fixed wing (VFW) is gaining significant attention, particularly in the transition phase from VTOL to fixed wing and vice versa. One of the latest and most challenging transition strategies is the bird take-off mode, where vertical and horizontal take-off is carried out simultaneously, mimicking the behavior of birds. The condition that is rarely considered when taking off is the ground effect. Under natural conditions, a ground effect is bound to occur, which can significantly impact the stability of the transition when the VFW is close to the ground. This paper addresses this issue by proposing a model and control strategy and conducting realistic visual 3D simulations of the VFW transition that incorporates ground effect using full complex aerodynamic parameters. This research represents a novel approach, using the robot operating system (ROS) and Gazebo to conduct realistic visual 3D simulations for VFW transition. The linear quadratic regulator (LQR) control method is used to manage the transitions and compensate for any disturbances. The flight tests demonstrate the effectiveness of the proposed model and controller in executing flight missions using the bird take-off mode transition. Moreover, the controller has demonstrated reliability and robustness in compensating for attitude errors induced by ground effects and external disturbances.

UAV (Unmanned Aerial Vehicle) can fly autonomously or be controlled remotely by a pilot. Quadrotor as one type of UAV has been widely implemented in various needs. Its system design has a lot of control techniques involved. The design starts with the physical modeling. Quadrotor physical modeling is modeling based on the laws of physics as a theory and mathematical modeling of physical interpretation. The problem arises when actual plants are not fit with mathematical models that are used as the control design before. Such discrepancy arises because of external interference, plant parameters, and dynamics models that are nonlinear. If control systems are not designed to deal with non-linear interference, it is difficult to us to maintain quadrotor flight. Therefore, we need control methods that can be applied to linear and nonlinear systems. Routh Stability can be used to generate PID (Proportional Integral and Derivative) constants as a linear control method by using a Ziegler-Nichols. Lyapunov as a method of non-linear control method offers distinct advantages over other control methods. Lyapunov second method is further implemented by a control technique that gives a good effect. So the PID and Lyapunov method can make quadrotor approaching the stationary state.

As one of the essential modules in intelligent surveillance systems, loitering detection plays an important role in reducing theft incidents by analyzing human behavior. This paper introduces a novel strategy for detecting the loitering activities of humans in the monitoring area for an intelligent surveillance system based on a vision sensor. The proposed approach combines spatial and temporal information in the feature extraction stage to decide whether the human movement can be regarded as loitering. This movement has been previously tracked using human detectors and particle filter tracking. The proposed method has been evaluated using our dataset consisting of 20 videos. The experimental results show that the proposed method could achieve a relatively good accuracy of 85% when utilizing the random forest classifier in the decision stage. Thus, it could be integrated as one of the modules in an intelligent surveillance system.