Fish object detection has attracted significant attention because of the considerable role that fish play in human society and ecosystems and the necessity to gather more comprehensive fish data through underwater videos or images. However, fish detection has always faced difficulties with the occlusion problem because of dense populations and underwater plants that obscure them, and no perfect solution has been found until now. To address the occlusion issue in fish detection, the following effort was made: creating a dataset of occluded fishes, integrating the innovative modules in Real-time Detection Transformer (RT-DETR) into You Only Look Once v8 (YOLOv8), and applying repulsion loss. The results show that in the occlusion dataset, the mAP of the original YOLOv8 is 0.912, while the mAP of our modified YOLOv8 is 0.971. In addition, our modified YOLOv8 also has better performance than the original YOLOv8 in terms of loss curves, F1–Confidence curves, P–R curves, the mAP curve and the actual detection effects. All these indicate that our modified YOLOv8 is suitable for fish detection in occlusion scenes.

High-resolution neutron radiography provides novel and stirring opportunities to investigate the structures of light elements encased by heavy elements. For this study, a series of Gd₂O₂S:Tb, F particles were prepared using a high-temperature solid phase method and then used as a scintillation screen. Upon reaching 293 nm excitation, a bright green emission originated from the Tb³⁺ luminescence center. The level of F doping affected the fluorescence intensity. When the F doping level was 8 mol%, the fluorescence intensity was at its highest. The absolute quantum yield of the synthesized particles reached as high as 77.21%. Gd₂O₂S:Tb, F particles were applied to the scintillation screen, showing a resolution on the neutron radiograph as high as 12 μm. These results suggest that the highly efficient Gd₂O₂S:Tb, F particles are promising scintillators for the purposes of cold neutron radiography.

Detecting transportation pipeline leakage points within chemical plants is difficult due to complex pathways, multi-dimensional survey points, and highly dynamic scenarios. However, hexapod robots’ maneuverability and adaptability make it an ideal candidate for conducting surveys across different planes. The path-planning problem of hexapod robots in multi-dimensional environments is a significant challenge, especially when identifying suitable transition points and planning shorter paths to reach survey points while traversing multi-level environments. This study proposes a Particle Swarm Optimization (PSO)-guided Double Deep Q-Network (DDQN) approach, namely, the PSO-guided DDQN (PG-DDQN) algorithm, for solving this problem. The proposed algorithm incorporates the PSO algorithm to supplant the traditional random selection strategy, and the data obtained from this guided approach are subsequently employed to train the DDQN neural network. The multi-dimensional random environment is abstracted into localized maps comprising current and next level planes. Comparative experiments were performed with PG-DDQN, standard DQN, and standard DDQN to evaluate the algorithm’s performance by using multiple randomly generated localized maps. After testing each iteration, each algorithm obtained the total reward values and completion times. The results demonstrate that PG-DDQN exhibited faster convergence under an equivalent iteration count. Compared with standard DQN and standard DDQN, reductions in path-planning time of at least 33.94% and 42.60%, respectively, were observed, significantly improving the robot’s mobility. Finally, the PG-DDQN algorithm was integrated with sensors onto a hexapod robot, and validation was performed through Gazebo simulations and Experiment. The results show that controlling hexapod robots by applying PG-DDQN provides valuable insights for path planning to reach transportation pipeline leakage points within chemical plants.

Cs₂LiYCl₆: Ce³⁺ (CLYC) is a dual-mode gamma-neutron scintillator with a medium gamma-ray resolution and pulse-shape discrimination (PSD) capability. The PSD performance of CLYC is greatly weakened when coupled with silicon photomultipliers (SiPMs) because of SiPMs’ low detection efficiency for the ultrafast Core-Valence-Luminescence (CVL) component under gamma excitation. In our previous work, the PSD Figure-of-Merit (FoM) value was optimized to 2.45 at the gamma-equivalent energy region of the thermal neutron by using the charge comparison method. However, this value was reduced to 1.37 at the lower gamma-equivalent energy region of more than 325 keV, and neutrons were difficult to distinguish from gamma rays. Hence, new algorithms should be studied to improve the PSD performance at low gamma-equivalent energy regions. Convolutional Neural Networks (CNNs) have excellent image recognition capabilities, and thus, neutron and gamma-ray waveforms can be discriminated by their characteristics through a known training set. In this study, neutron and gamma-ray waveforms were measured with a ¹³⁷Cs source and moderated ²⁵²Cf source via an SiPM array-coupled CLYC detector and divided into two groups: training and PSD testing. The CNN training set comprised ¹³⁷Cs characteristic gamma-ray waveforms and thermal neutron waveforms that were discriminated by the charge comparison method from the training group. A CNN with two convolution-pooling layers was designed to accomplish PSD with the test group. The PSD FoM value of the CNN method was calculated to be 37.20 at the gamma-equivalent energy region of more than 325 keV. This result was much higher than that of the charge comparison method, indicating that neutrons and gamma rays could be better distinguished with the CNN method, especially at low gamma-equivalent energy regions.

³He is a splendid neutron detection material due to its high neutron reaction cross section, gaseous state, and nonelectronegative and nonpoisonous nature. With the worldwide problem of the “³He supply crisis” arising, boron-lined gaseous neutron detectors are being widely used in neutron detection to replace ³He neutron detectors. In this work, to reduce the scattering neutron background coming from the substrate of a boron-lined neutron detector in the application of neutron scattering, a new design of the boron-lined gaseous neutron detector composed of a boron-lined multichip converter and a multiwire proportional chamber was proposed. The electron drift efficiency matrix simulated by Garfield++ (Version 2023.4) and the values and positions of electron energy deposition simulated by Geant4 were obtained. The α, ⁷Li, and total charged particle energy deposition spectra were acquired via coupling calculations of the electron drift efficiency matrix and the values and positions of electron energy deposition, and the width of the slit was selected as 3 mm. The boron-lined multilayer converter neutron detector (BMCND) was tested using a ²⁴¹Am–²³⁹Pu mixture α source, and the total count rate of α charged particles was measured as 599.5 s⁻¹, which is 89% of the theoretical α particle emission rate of 672.9 s⁻¹. The drift voltage experiments showed that 1200 V is enough to acquire a relatively ideal count, and a 2500 V drift voltage was confirmed, considering the higher count and instrument safety. We also performed the neutron detection experiments using a photo-neutron source, and a characteristic spectrum shape of “two stairs” was measured. When borated polyethylene was used to shield the BMCND, the detected total count decreased while keeping the characteristic spectrum shape, demonstrating that the BMCND was equipped with the ability to detect neurons, indicating that BMCNDs have the potential to be an outstanding ³He alternative neutron detector.