Robust Deep Learning Model for Black Fungus Detection Based on Gabor Filter and Transfer Learning

Black fungus is a rare and dangerous mycology that usually affects the brain and lungs and could be life-threatening in diabetic cases.Recently,some COVID-19 survivors,especially those with co-morbid diseases,have been susceptible to black fungus.Therefore,recovered COVID-19 patients should seek medical support when they notice mucormycosis symptoms.This paper proposes a novel ensemble deep-learning model that includes three pre-trained models:reset(50),VGG(19),and Inception.Our approach is medically intuitive and efficient compared to the traditional deep learning models.An image dataset was aggregated from various resources and divided into two classes:a black fungus class and a skin infection class.To the best of our knowledge,our study is the first that is concerned with building black fungus detection models based on deep learning algorithms.The proposed approach can significantly improve the performance of the classification task and increase the generalization ability of such a binary classification task.According to the reported results,it has empirically achieved a sensitivity value of 0.9907,a specificity value of 0.9938,a precision value of 0.9938,and a negative predictive value of 0.9907.

Smart control system for the precision cultivation of black fungus

Black fungus,with high nutritional and medicinal value,has been cultivated in China for a long time,and Heilongjiang alone accounts for about 40%of the global output.At present,the cultivation of black fungus derives mainly from the inheritance of relatively primitive practices and experience of farmers,resulting in inconsistent quality of fungus.In this study,a smart control system for the precision cultivation of black fungus was designed by using intelligent detection and control technology.The system includes a precision culture test environment and remote control system.The precision cultivation environment contains four sub-independent environments.The key parameters such as temperature,humidity,and light behavior were collected and can be adjusted individually,according to the precision cultivation stages.The intelligent remote control system included a controller cabinet,sensors unit,temperature control unit,humidity control unit,light control unit,and information transmitting unit.The controller cabinet includes a key controller which can auto-control the temperature,humidity,and lightly adjust components according to the precision cultivation conditions and processing.The temperature sensors were installed in a 3D array close to the fungus bags about 5 cm in rooms.The light tape was installed on the six walls and also had three colors(Red,Blue,and Green)which could be controlled independently in each room.The control strategy through the analysis of the data collected by all sensors,the current cultivate situation of the cultivation environment was obtained,and the heater,fan,light,and nozzle were regulated according to the strategy to maintain a suitable precision cultivation environment for fungus.To verify the feasibility of the precision cultivation processing and control system,the test result shows that the error of temperature control was about 0℃-1℃,the error of humidity control was about 1%-4%,and the error of illuminance control was about 0-50 lx;All the verification results show that the control system for precision cultivation has high precision and can meet the needs of exploring the"Black 29"fungus cultivation experiment environment.Based on the orthogonal experiment,the best combination of the temperature and humidity for each growth stage was also investigated in this study,further proving the reliability and feasibility of the control system for the precision cultivation of Auricularia auricula.