This study investigates the use of Hyperspectral Images (HSI) in remote sensing technology, focusing on the challenges of open-set classification. The high-dimensionality and complexity of HSI bring unparalleled depth and precision to remote sensing, yet pose significant classification challenges. To address these challenges, we introduce a novel prototype network based on feature invariance for open-set HSI classification (FIWPPN). This network utilizes a ResNet architecture to extract spectral-spatial features and includes an invariance clustering module to enhance feature boundary delineation in the prototype network classification. Furthermore, we have developed a weighted Pearson distance metric to establish a measurement domain between unlabeled data and training data, facilitating open-set recognition. Experimental validation on three publicly accessible HSI datasets demonstrates that our method surpasses existing classification techniques in terms of classification accuracy and open-set classification performance.

In order to improve the electrical characteristics of transformer oil-impregnated pressboard, transformer oil-based nanofluids were used to impregnate pressboards. It is found that nanofluid-impregnated pressboard (NP) exhibits substantially higher AC and DC breakdown voltage than that of pure oil-impregnated pressboard (OP). Pulse electroacoustic measurement (PEA) was carried out to study the difference of space charge distribution and decay characteristic in OP and NP. It has demonstrated that NP has a more uniform internal electric field, which is caused by a higher charge transport rate compared to OP, resulting in the improved electrical insulating properties.

Space-based spectral radiation detection is one of the most effective approaches for detecting hypersonic vehicles. However, due to complex characteristics of the plasma sheath that is generated by aerodynamic thermal effect and envelopes hypersonic vehicle, space-based spectral radiation detection is still confronted with great challenges. Based on the mechanisms of spectral radiation and transmission, we establish a model to conduct optimal selection on spectral wavebands for detecting hypersonic vehicle. Through using the established model, we obtain the spectral radiation characteristics of plasma-sheath-enveloped vehicles (RAM-CII and HTV2) under different flight conditions (at 40–70-km altitude with 10–25-Mach velocity). The optimal spectral wavebands for space-based detection are analyzed and identified using the calculated spectral data, upon which the results reveal that significant differences exist in spectral radiation intensities of different flight status for those two vehicles. The overall radiation intensity of RAM-CII vehicle is higher than that of HTV2 vehicle, to which the optimized detection wavebands corresponding to velocity and altitude differ. Generally, at different altitudes, the optimal wavebands for both vehicles are 5.00–7.86, 2.59–3.44, and 1.81–2.10 $\mu $ m. At different flight speeds, the optimal bands are 0.78–1.13 $\mu $ m and 99–130 nm, respectively. Combined with the optimized speed and height bands, the optimal detection bands of RAM-CII vehicle and HTV2 vehicle are 5.00–7.86 $\mu $ m, 2.59–3.44 $\mu $ m, and 99–130 nm. The above findings can provide useful data for in-depth study of space-based spectral radiation detection.

Most of the existing anomaly detection (AD) approaches for hyperspectral images (HSIs) usually achieve high detection accuracy at the cost of high computational complexity. To meet the needs of actual detection scenarios (efficiency, robustness, and accuracy), this letter introduces a fast and robust AD algorithm via subfeatures grouping and binary accumulation (SFBA) for HSIs. We propose a spatial–spectral anomaly scoring strategy to improve detection accuracy. A number of spectral subfeatures of HSI are selected and divided into $N$ groups as the detection input information and the proposed scoring strategy is carried out for $N$ group data, respectively, to improve the detection efficiency. Then binary accumulation is introduced to improve the robustness of AD algorithm by accumulating detection results of each group. Our proposed detection algorithm was compared with the existing algorithms on real hyperspectral datasets, thereby verifying its strong robustness and low computational complexity simultaneously.

Existing approaches addressing the few-shot open-set recognition (FSOSR) challenge in hyperspectral images (HSIs) often encounter limitations stemming from sparse labels, restricted category numbers, and low openness. These limitations compromise stability and adaptability. In response, an open-set HSI classification algorithm based on data wandering (DW) is introduced in this research. Firstly, a K-class classifier suitable for a closed set is trained, and its internal encoder is leveraged to extract features and estimate the distribution of known categories. Subsequently, the classifier is fine-tuned based on feature distribution. To address the scarcity of samples, a sample density constraint based on the generative adversarial network (GAN) is employed to generate synthetic samples near the decision boundary. Simultaneously, a mutual-point learning method is incorporated to widen the class distance between known and unknown categories. In addition, a dynamic threshold method based on DW is devised to enhance the open-set performance. By categorizing drifting synthetic samples into known and unknown classes and retraining them together with the known samples, the closed-set classifier is optimized, and a (K + 1)-class open-set classifier is trained. The experimental results in this research demonstrate the superior FSOSR performance of the proposed method across three benchmark HSI datasets.

Nanofluids were fabricated by employing nanoparticles with different dielectric properties as modifiers to improve the dielectric performance of the mineral oil. Breakdown voltages under AC and lighting impulse stresses were measured to evaluate breakdown strength of these nanofluids. The results indicated that the addition of semiconductive nanoparticles to the base oil can improve the breakdown strength at the optimum concentration of nanoparticle. However, the insulating nanoparticles were unfavorable for the overall dielectric strength of the nanofluids. A possible mechanism was discussed based on the physical properties of the suspended nanoparticles.