Mobile Robot Application with Hierarchical Start Position DQN.

Advances in deep learning significantly affect reinforcement learning, which results in the emergence of Deep RL (DRL). DRL does not need a data set and has the potential beyond the performance of human experts, resulting in significant developments in the field of artificial intelligence. However, because a DRL agent has to interact with the environment a lot while it is trained, it is difficult to be trained directly in the real environment due to the long training time, high cost, and possible material damage. Therefore, most or all of the training of DRL agents for real-world applications is conducted in virtual environments. This study focused on the difficulty in a mobile robot to reach its target by making a path plan in a real-world environment. The Minimalistic Gridworld virtual environment has been used for training the DRL agent, and to our knowledge, we have implemented the first real-world implementation for this environment. A DRL algorithm with higher performance than the classical Deep Q-network algorithm was created with the expanded environment. A mobile robot was designed for use in a real-world application. To match the virtual environment with the real environment, algorithms that can detect the position of the mobile robot and the target, as well as the rotation of the mobile robot, were created. As a result, a DRL-based mobile robot was developed that uses only the top view of the environment and can reach its target regardless of its initial position and rotation.

Development and validation of a new RP-HPLC method for organic explosive compounds.

A new RP-HPLC method was developed and validated to achieve the separation and quantification of the organic explosive compounds such as pentaerythritol tetranitrate (PETN), 1-methyl-2,4,6-trinitro toluen (TNT), picric acid, 1,3,5,7-tetrazocine (HMX), cyclorimethylenetrinitramine (RDX), 2,4,6 Tri nitro phenyl methyl nitramine (Tetryl), 1-methyl-2,4-dinitro toluen (DNT), ethylene glycol dinitrate (EGDN), and trinitroglycerine (TNG) in this study. The mobile phase composition (IPA percentage in water) and the flow rate was optimized for the separation of the organic explosive compounds. Theoretical plate number (N), capacity factor (k'), resolution (Rs) were used to determine the optimum chromatographic conditions. The most favorable conditions were detected as 22% IPA in water, a flow rate of 1.7 mL/min. Under optimum chromatographic conditions, separation was completed within 18 min. The linear ranges were 6.5-100 and 10-0.625 mg/L (R2 = 0.998-0.999) for investigated explosives. Mean recoveries were found to be in the range of 95.3%-103.3%. LOD and LOQ were ranged between 0.09-1.32 mg/L and 0.31-4.42 mg/L, respectively, for investigated explosives. The obtained results showed that the new method was very suitable for the separation of the resolution of organic explosive compounds with C18 columns. TNT and RDX seized from terrorists were found to be in 372.99 mg/L and 79.55 mg/L, respectively.

Ear as an alternative sampling site for GSR analysis following shotgun discharge.

Detection of GSR particles potentially indicates that a person fired a gun or somehow involved to a shooting event. GSR on the shooter's hand, face, and clothing may disappear within hours and with sweat secretion, washing or cleaning to remove evidences. Due to its anatomical properties, ears are relatively protected; therefore, we aimed to identify GSR particles on ears, to compare its anatomical parts of ears, and compare ears with common GSR sampling sites, based on firing frequency. A 12-gauge semi-automatic shotgun was used. In the 4-week study, one shot in the first week, two consecutive shots in second week, three shots in third week, and five shots in fourth week were fired by six participants. Samples were taken from MAE, CA, and AAECA of both ears and common GSR sampling sites. The characteristic 3-component structure (Pb/Sb/Ba) of the samples was analyzed by SEM/EDX. Right CA was the most suitable area for sampling, which might be attributed to posture of body during targeting. Right ear was the most suitable area to take samples from CA or MAE in 3-shot group. Besides, left AAECA in 1- and 2-shot groups and the left MAE in 5-shot group were the most suitable areas for GSR sampling. In conclusion, ear seems to be a valuable alternative for detection of GSR particles, due to its complex anatomical structure potentially preventing loss of GSR with daily cleaning. Findings suggested that crime scene investigation teams and criminal laboratory staff should consider ear as a valuable alternative for GSR detection.