Security identification solutions against WLAN network attacks according to straightforward digital detectors, such as SSID, IP addresses, and MAC addresses, are not efficient in identifying such hacking or router impersonation. These detectors can be simply mocked. Therefore, a further protected key uses new information by combining these simple digital identifiers with an RF signature of the radio link. In this work, a design of a convolutional neural network (CNN) based on fingerprinting radio frequency (RF) is developed with computer-generated data. The developed CNN is trained with beacon frames of a wireless local area network (WLAN) that is simulated as a result of identified and unidentified router nodes of fingerprinting RF. The proposed CNN is able to detect router impersonators by comparing the data pair of the MAC address and RF signature of the received signal from the known and unknown routers. ADAM optimizer, which is the extended version of stochastic gradient descent, has been used with a developed deep learning convolutional neural network containing three fully connected and two convolutional layers. According to the training progress graphic, the network converges to around 100% accuracy within the first epoch, which indicates that the developed architecture was efficient in detecting router impersonations.

While the motion planning algorithms consider the obstacles that were known in the map, it is possible to use obstacle avoidance algorithms to take over and send commands to theunmanned aerial vehicle (UAV), when there is an unknown obstacle on the way. The rapidly random tree (RRT) algorithm is used to plan paths for a quad-copter or a fixed-wing UAV. This work develops a model for UAV with fixed-wing using a 3D map exploring the RRT technique. The first step is to obtain a 3D occupancy map from the map data stored in the UAV city to provide a map with some pre-generated obstacles. The contribution of this work is to use RRT planning for 3D state space, where the motion segment or motion primitive connecting the two consecutive states should be defined in a 3D space while satisfying the motion constraints of a UAV. The simulation includes setting up a 3D map, providing the starting and destination pose, planning a way using RRT and 3D Dubins moving primitives, smoothing the acquired trajectory, and simulating the UAV flight. The results obtained demonstrate that the smoothed-generated waypoints significantly improved tracking in general with shorter paths.

To make robotic hand devices controlled by surface electromyography (sEMG) signals feasible and practical tools for assisting patients with hand impairments, the problems that prevent these devices from being widely used have to be overcome. The most significant problem is the involuntary amplitude variation of the sEMG signals due to the movement of electrodes during forearm motion. Moreover, for patients who have had a stroke or another neurological disease, the muscle activity of the impaired hand is weak and has a low signal-to-noise ratio (SNR). Thus, muscle activity detection methods intended for controlling robotic hand devices should not depend mainly on the amplitude characteristics of the sEMG signal in the detection process, and they need to be more reliable for sEMG signals that have a low SNR. Since amplitude-independent muscle activity detection methods meet these requirements, this paper investigates the performance of such a method on people who have had a stroke in terms of the detection of weak muscle activity and resistance to false alarms caused by the involuntary amplitude variation of sEMG signals; these two parameters are very important for achieving the reliable control of robotic hand devices intended for people with disabilities. A comparison between the performance of an amplitude-independent muscle activity detection algorithm and three amplitude-dependent algorithms was conducted by using sEMG signals recorded from six hemiparesis stroke survivors and from six healthy subjects. The results showed that the amplitude-independent algorithm performed better in terms of detecting weak muscle activity and resisting false alarms.

Deep learning algorithms are able to automatically handle point clouds over a broad range of 3D imaging implementations. They have applications in advanced driver assistance systems, perception and robot navigation, scene classification, surveillance, stereo vision, and depth estimation. According to prior studies, the detection of objects from point clouds of a 3D dataset with acceptable accuracy is still a challenging task. The Point-Pillars technique is used in this work to detect a 3D object employing 2D convolutional neural network (CNN) layers. Point-Pillars architecture includes a learnable encoder to use Point-Nets for learning a demonstration of point clouds structured with vertical columns (pillars). The Point-Pillars architecture operates a 2D CNN to decode the predictions, create network estimations, and create 3D envelop boxes for various object labels like pedestrians, trucks, and cars. This study aims to detect objects from point clouds of a 3D dataset by Point-Pillars neural network architecture that makes it possible to detect a 3D object by means of 2D convolutional neural network (CNN) layers. The method includes producing a sparse pseudo-image from a point cloud using a feature encoder, using a 2D convolution backbone to process the pseudo-image into high-level, and using detection heads to regress and detect 3D bounding boxes. This work utilizes an augmentation for ground truth data as well as additional augmentations of global data methods to include further diversity in the data training and associating packs. The obtained results demonstrated that the average orientation similarity (AOS) and average precision (AP) were 0.60989, 0.61157 for trucks, and 0.74377, 0.75569 for cars.