Amid the COVID-19 pandemic, prevention and control measures became normalized, prompting the development of campuses from digital to intelligent, eventually evolving to become wise. Current cutting-edge technologies include big data, Internet of Things, cloud computing, and artificial intelligence drive campus innovation, but there are still problems of unintuitive scenes, lagging monitoring information, untimely processing, and high operation and maintenance costs. Based on this, this study proposes the use of digital twin technology to digitally construct the physical campus scene, fully digitally represent it, accurately map the physical campus to the virtual campus with real-time sensing, and remotely control it to achieve the reverse control of the twin virtual campus to the physical campus. The research is guided by the theoretical model proposed by the digital twin technology, using UAV tilt photography and 3D modelling to collaboratively build the virtual campus scene. At the design stage, the interactive channel of the system is developed based on Unity3D to the realize real-time monitoring, decision making and prevention of dual spatial data. A design scheme of the spiral optimization system life cycle is formed. The modules of the smart campus system were evaluated using a system usability scale based on student experience. The experimental results show that the virtual-real campus system can enhance school management and teaching, providing important implications for promoting the development and application of campus intelligent systems.

Traditional soil nitrogen detection methods have the characteristics of being time-consuming and having an environmental pollution effect. We urgently need a rapid, easy-to-operate, and non-polluting soil nitrogen detection technology. In order to quickly measure the nitrogen content in soil, a new method for detecting the nitrogen content in soil is presented by using a near-infrared spectrum technique and random forest regression (RF). Firstly, the experiment took the soil by the Xunsi River in the area of Hubei University of Technology as the research object, and a total of 143 soil samples were collected. Secondly, NIR spectral data from 143 soil samples were acquired, and chemical and physical methods were used to determine the content of nitrogen in the soil. Thirdly, the raw spectral data of soil samples were denoised by preprocessing. Finally, a forecast model for the soil nitrogen content was developed by using the measured values of components and modeling algorithms. The model was optimized by adjusting the changes in the model parameters and Gini coefficient (∆Gini), and the model was compared with the back propagation (BP) and support vector machine (SVM) models. The results show that: the RF model modeling set prediction R²_C is 0.921, the RMSEC is 0.115, the test set R²_P is 0.83, and the RMSEP is 0.141; the detection of the soil nitrogen content can be realized by using a near-infrared spectrum technique and random forest algorithm, and its prediction accuracy is better than that of the BP and SVM models; using ∆ Gini to optimize the RF modeling data, the spectral information of the soil nitrogen content can be extracted, and the data redundancy can be reduced effectively.

As a new non-destructive testing technology, near-infrared spectroscopy has broad application prospects in agriculture, food, and other fields. In this paper, an intelligent near-infrared diffuse reflectance spectroscopy scheme (INIS) for the non-destructive testing of the sugar contents in vegetables and fruits was proposed. The cherry tomato were taken as the research object. The applicable objects and features of the three main methods of near-infrared detection were compared. According to the advantages and disadvantages of the three near infrared (NIR) detection methods, the experiment was carried out. This experiment involved the near-infrared diffuse reflection detection method, and the back propagation (BP) network model was established to research the sugar content of the cherry tomatoes. We used smoothing and a principal component analysis (PCA) to extract the final spectrum from the experimental spectrum. Taking the preprocessed spectral data as the input of the network and the measured sugar content of the cherry tomatoes as the output, the 80-12-1 network model structure was established. The cross-validation coefficient of determination was 0.8328 and the mean absolute deviation was 0.5711. The results indicate that the BP neural network can quickly and effectively detect the sugar content in cherry tomatoes. This intelligent near-infrared diffuse reflectance spectroscopy (INIS) scheme can be extended and optimized for almost all sugar-containing fruits and vegetables in the future.

To study on the thermoelectric power generation for industrial waste heat recovery applied in a hot-air blower, an experimental thermoelectric generator (TEG) bench with the hexagonal heat exchanger and commercially available Bi₂Te₃ thermoelectric modules (TEMs) was established, and its performance was analyzed. The influences of several important influencing factors such as heat exchanger material, inlet gas temperature, backpressure, coolant temperature, clamping pressure and external load current on the output power and voltage of the TEG were comparatively tested. Experimental results show that the heat exchanger material, inlet gas temperature, clamping pressure and hot gas backpressure significantly affect the temperature distribution of the hexagonal heat exchanger, the brass hexagonal heat exchanger with lower backpressure and coolant temperature using ice water mixture enhance the temperature difference of TEMs and the overall output performance of TEG. Furthermore, compared with the flat-plate heat exchanger, the designed hexagonal heat exchanger has obvious advantages in temperature uniformity and low backpressure. When the maximum inlet gas temperature is 360 °C, the maximum hot side temperature of TEMs is 269.2 °C, the maximum clamping pressure of TEMs is 360 kg/m², the generated maximum output power of TEG is approximately 11.5 W and the corresponding system efficiency is close to 1.0%. The meaningful results provide a good guide for the system optimization of low backpressure and temperature-uniform TEG, and especially demonstrate the promising potential of using brass hexagonal heat exchanger in the automotive exhaust heat recovery without degrading the original performance of internal combustion engine.

Marine pollution significantly impacts the sustainable development of marine ecosystems and the marine economy. Accurate detection of marine debris is essential for effective pollution control. However, existing high-precision detection algorithms are challenging to deploy on performance-constrained IoT underwater devices due to their large computational complexity and model size. To address this issue, this paper introduces YOLO-MES, an innovative underwater debris detection algorithm that integrates a lightweight design and a feature enhancement mechanism to enable efficient model deployment while preserving high accuracy. Unlike traditional YOLO models, YOLO-MES incorporates MobileNetV3 into underwater target detection, replacing the CSPDarknet backbone network, and optimizes the C3 and Conv layers through the bneck structure, significantly reducing computational demands and parameter scale at the architectural level. Additionally, YOLO-MES embeds the Efficient Channel Attention (ECA) module within the bneck structure to form the MECAneck module, which enhances adaptive feature extraction, significantly improving the network's cross-channel feature capture and target recognition capabilities. This paper also proposes a streamlined Slim-neck design strategy, which effectively reduces the number of parameters in the neck network while maintaining multi-scale feature fusion accuracy. Experimental results indicate that YOLO-MES achieves 95.8% accuracy on the dataset, while reducing model size and computational complexity by 64% and 67%, respectively. Compared to existing mainstream detection algorithms, YOLO-MES offers significant advantages in lightweight design and computational efficiency, providing a practical and deployable solution for underwater target detection on mobile devices.

Given the problems of using traditional training methods and insufficient funds in college sports agility training, the agility training system based on Wireless MESH Network is developed. The lower computer realizes the automatic networking between nodes based on the ESP-MESH network, and describes the networking process, intra-group communication and network management of the MESH network in detail. When the number of network layers ≤2, the node response time is about 300ms, and the packet loss rate is close to 0, it is proved that the Wireless MESH Network can transmit network data in real-time. The upper computer adopts the software design based on Android, which can view the agility training time of each point in the movement. In this paper, 10 university sports students were trained in stages for up to 9 weeks with the aid of an agility apparatus. After the training, the ability of rapid direction change, movement change and decision-making related to agile quality was significantly improved compared with those before the training (p < 0.01). The experimental results show that agile coaches are practical in improving college students’ agility.