In order to alleviate bottlenecks such as the lack of professional teachers, inattention during training processes, and low effectiveness in concentration training, we have proposed an immersive human–robot interactive (HRI) game framework based on deep learning for children’s concentration training and demonstrated its use through human–robot interactive games based on gesture recognition. The HRI game framework includes four functional modules: video data acquisition, image recognition modeling, a deep learning algorithm (YOLOv5), and information feedback. First, we built a gesture recognition model containing 10,000 pictures of children’s gestures, using the YOLOv5 algorithm. The average accuracy in recognition trainingwas 98.7%. Second, we recruited 120 children with attention deficits (aged from 9 to 12 years) to play the HRI games, including 60 girls and 60 boys. In the HRI game experiment, we obtained 8640 sample data, which were normalized and processed.According to the results, we found that the girls had better visual short-term memory and a shorter response time than boys. The research results showed that HRI games had a high efficacy, convenience, and full freedom, making them appropriate for children’s concentration training.

This paper focuses on the problem of intelligent evacuation route planning for emergencies, including natural and human resource disasters and epidemic disasters, such as the COVID-19 pandemic. The goal of this study was to quickly generate an evacuation route for a community for victims to be evacuated to safe areas as soon as possible. The evacuation route planning problem needs to determine appropriate routes and allocate a specific number of victims to each route. This paper formulates the problem as a maximum flow problem and proposes a binary search algorithm based on a maximum flow algorithm, which is an intelligent optimization evacuation route planning algorithm for the community. Furthermore, the formulation is a nonlinear optimization problem because each route’s suggested evacuation time is a convex nonlinear function of the number of victims assigned to that route. Finally, numerical examples and Matlab simulations demonstrate not only the algorithm’s effectiveness, but also that the algorithm has low complexity and high precision. The study’s findings offer a practical solution for nonlinear models of evacuation route planning, which will be widely used in human society and robot path planning schemes.

This paper presents a new scheme of a cost-effective tunable millimeter-wave (MMW) frequency synthesizer based on an ultra-wideband electro-optic frequency comb. The architecture for the quasi-tunable millimeter-wave frequency synthesizer mainly consists of a compact ultra-wide flat electro-optic frequency comb and a multi-tone frequency generator, which only includes a quantum dot mode-locked laser, a LiNbO${}_3$ dual-driving Mach–Zehnder modulator (DD-MZM) and Uni-traveling-carrier photodiode (UTC-PD). MMW signals generated with a quasi-tunable frequency are experimentally demonstrated. The difference in power is obtained for the different frequencies. The linewidth of the quasi-tunable frequency signals is less than 273 Hz. In addition, the single side band (SSB) phase noise of the 25, 37.5, 50 and 75 GHz is measured as −115, −106, −102 and −95 dBc/Hz at an offset of 1 kHz, respectively. The proposed frequency synthesizer has ultra-low phase noise, quasi-tunable frequency and simple structure. The research results of the frequency synthesizer are applied for 5G+ transmission with radio wave working at K-band and V-band. The flexible, compact and robust MMW frequency synthesizer is suitable for the future of ultra-high capacity 5G+ communication.

This paper proposes a compact and tunable plasmon modulator based on a metal-grating/graphene hybrid structure, aiming to overcome the critical bottlenecks of conventional modulators in terms of integration density and dynamic tunability. The device employs two metallic gratings that generate a periodic alternating electric field in the graphene when opposite voltages are applied across the two gratings, resembling an interdigitated electrode configuration. This electric field spatially modulates the carrier density in the graphene layer, forming an equivalent Bragg grating whose duty cycle and groove depth can be dynamically tuned by adjusting the voltage amplitude, thereby enabling modulation of propagating surface plasmon polaritons in graphene. The proposed modulator, based on dual-parameter control of the Bragg grating, achieves a 10 dB enhancement in maximum modulation depth over single-parameter (groove depth) modulation, with a compact footprint of 1 μm × 0.6 μm × 1 μm, a center-wavelength tuning range of 1.0 μm, and an FWHM tuning range of 0.55 μm. This compact and tunable modulator holds significant promise for applications in mid-infrared communication and integrated photonic chips.