As a large agricultural and population country, China’s annual demand for food is significant. The crop yield will be affected by various natural disasters every year, and one of the most important factors affecting crops is the impact of insect pests. The key to solving the problem is to detect, identify and provide feedback in time at the initial stage of the pest. In this paper, according to the pest picture data obtained through the pest detection lamp in the complex natural background and the marking categories of agricultural experts, the pest data set pest rotation detection (PRD21) in different natural environments is constructed. A comparative study of image recognition is carried out through different target detection algorithms. The final experiment proves that the best algorithm for rotation detection improves mean Average Precision by 18.5% compared to the best algorithm for horizontal detection, reaching 78.5%. Regarding Recall, the best rotation detection algorithm runs 94.7%, which is 7.4% higher than horizontal detection. In terms of detection speed, the rotation detection time of a picture is only 0.163s, and the model size is 66.54MB, which can be embedded in mobile devices for fast detection. This experiment proves that rotation detection has a good effect on pests’ detection and recognition rate, which can bring new application value and ideas, provide new methods for plant protection, and improve grain yield.

Detection of methane is a vital aspect of environment security in coal mining. At present, catalytic sensors are widely used. A new structure sensor of methane gas had been designed and fabricated. The Pt resistance for temperature and heater is on the silicon membrane with micro air bridge structure. The sensor has advantages of simple structure, easy processing and high accuracy compared to normal sensors. The sensitive element is a platinum temperature sensor that measures the heat of combustion liberated as the combustible analyte is oxidized on its catalytic surface covered with a layer of doped porous alumina. Sputtering technique, lithography and so on are mainly adopted to fabricate the element's Pt film heating resistance. The fabrication of the heating resistance is a crucial step in this experiment. The heating resistances are completed under all- same technique. So the heating resistances' value will be in good concordance. Methane generally needs high temperature to support its normal work. To meet this temperature region, the element's power consumption will be high if the element's body resistance is big. In order to decrease the element's power consumption, it is necessary to decrease the body resistance. As the traditional sensitive element, to get high sensitivity, it is necessary to put some catalyst into the sensitive film material as PdCl₂. Because of micro-fabrication (MEMS) techniques, catalytic sensors are likely to be smaller and more lower power consumption.

The temperature effect is one of the critical factors to induce the resonance wavelength shift in fiber-optic surface plasmon resonance (SPR) sensors, which leads to the inaccuracy measurement of refractive index (RI) in practical applications. In this study, a novel dual-wavelength method is presented for fiber-optic SPR sensors to measure the changes of RI and temperature simultaneously in real time. A typical model of an SPR-based fiber optical sensor is constructed for theoretical analysis of temperature effect. Both the thermo-optic effect in the fiber core and phonon–electron scattering along with electron–electron scattering in the metal layer are studied systematically in the theoretical model. The linear and independent relationship, about the dependence of defined output signals on the RI and temperature, is validated by a theoretical calculation in specific dual wavelengths. A proof-of-concept experiment is conducted to demonstrate the capability of the presented dual-wavelength technique. The experimental results indicate that the presented dual-wavelength method is technically feasible and can be applied for practical application. Since the presented method only depends on the full advantages of the transfer spectrum data, it can be applied directly to the conventional single-channel fiber-optic SPR without any specific design structure of the sensor probe. The proposed method provides a new way to detect the RI under different thermal conditions and could lead to a better design for the fiber-optic SPR sensors.

Fully automated immunoassay analyzers are integral to clinical testing, with liquid-level detection crucial to mitigate false measurements and cross-contamination. This study introduces a bubble detection algorithm based on the Random Forest machine learning model to address bubble detection in analyzers using capacitive sensors. The algorithm processes collected capacitance data, accurately identifying bubbles and ensuring sampling accuracy. Data preprocessing, feature extraction, and classification enable precise bubble detection. Compared to the traditional CART decision tree algorithm, this algorithm demonstrates superior bubble detection performance, indicating its significant research value and potential for liquid-level detection in fully automated immunoassay analyzers.