Underwater Biological Detection Algorithm Based on Improved Faster-RCNN

Underwater organisms are an important part of the underwater ecological environment. More and more attention has been paid to the perception of underwater ecological environment by intelligent means, such as machine vision. However, many objective reasons affect the accuracy of underwater biological detection, such as the low-quality image, different sizes or shapes, and overlapping or occlusion of underwater organisms. Therefore, this paper proposes an underwater biological detection algorithm based on improved Faster-RCNN. Firstly, the ResNet is used as the backbone feature extraction network of Faster-RCNN. Then, BiFPN (Bidirectional Feature Pyramid Network) is used to build a ResNet–BiFPN structure which can improve the capability of feature extraction and multi-scale feature fusion. Additionally, EIoU (Effective IoU) is used to replace IoU to reduce the proportion of redundant bounding boxes in the training data. Moreover, K-means++ clustering is used to generate more suitable anchor boxes to improve detection accuracy. Finally, the experimental results show that the detection accuracy of underwater biological detection algorithm based on improved Faster-RCNN on URPC2018 dataset is improved to 88.94%, which is 8.26% higher than Faster-RCNN. The results fully prove the effectiveness of the proposed algorithm.

A Review of Off–On Fluorescent Nanoprobes: Mechanisms, Properties, and Applications

With the development of nanomaterials, fluorescent nanoprobes have attracted enormous attention in the fields of chemical sensing, optical materials, and biological detection. In this paper, the advantages of “off–on” fluorescent nanoprobes in disease detection, such as high sensitivity and short response time, are attentively highlighted. The characteristics, sensing mechanisms, and classifications of disease-related target substances, along with applications of these nanoprobes in cancer diagnosis and therapy are summarized systematically. In addition, the prospects of “off–on” fluorescent nanoprobe in disease detection are predicted. In this review, we presented information from all the papers published in the last 5 years discussing “off–on” fluorescent nanoprobes. This review was written in the hopes of being useful to researchers who are interested in further developing fluorescent nanoprobes. The characteristics of these nanoprobes are explained systematically, and data references and supports for biological analysis, clinical drug improvement, and disease detection have been provided appropriately.

Dynamic Characterization of Biosensing MEMS Cantilevers with Different Position of the Driving Electrode—Vacuum Response Versus Ambient Conditions

The influence of the driving electrode positions on the dynamic response of polysilicon MEMS resonators used in biosensing applications is studied as a function of the operating conditions (vacuum versus free-air operating mode). The scope of this research work is orientated towards identifying the effect of driving electrode position on the dynamic response of sensing MEMS used in biomass detection. The mass-deposition detection is based on the change in the resonant frequency of vibrating elements considering a biological detection film deposited on the oscillating structure. The operating conditions, such as medium pressure, change the behavior of the dynamic response including the resonant frequency, the amplitude, and the velocity of oscillations as well as the quality factor and the loss of energy. The change in the dynamic response of the investigated MEMS cantilevers as a function of the lower electrode position and operating conditions is evaluated using a Polytec Laser Vibrometer. The decrease in the amplitude and velocity of the oscillations if the lower electrode is moved from the beam free-end toward the beam anchor is experimentally monitored. The changes in the response of samples in vacuum are slightly influenced by the electrode position compared with the response of the same sample in ambient conditions. Moreover, the effect of oscillating modes (first, second and third modes) is taken into consideration to improve the dynamical detection of the investigated samples. The obtained results indicate that different responses of MEMS resonators can be achieved if the position of the driving electrode is moved from the cantilever free-end toward the anchor. Indeed, the resonator stiffness, velocity and amplitude of oscillations are significantly modified for samples oscillating in ambient conditions for biological detection compared with their response in vacuum.