No abstract

As a kind of important insect pest of cotton crops, aphids cause serious damage in cotton yields and quality worldwide, posing a significant risk to economic losses. Automatic detection of the pest damage level plays an important role in cotton field management. However, it is usually regarded as a classification problem in machine learning, where the disease severity levels are taken as independent categories and the inter-level relationship has not fully been considered. To utilize the inherited relations among different severity levels caused by cotton aphids, a novel approach based on the spectral index reconstruction was proposed in this study. First, six types of initial spectral indices were reconstructed based on healthy samples in the training set. Then, the severity sequences corresponding to the reconstructed initial spectral indices (RISIs) were sorted and compared with the ideal sequence. After attaining sequences most consistent with the ideal one, the ratio between the inter- and intra- levels was calculated to select the sensitive RISI. Moreover, the range of each severity level was established by the thresholds between adjacent grades of the selected sensitive RISI, which was finally used to determine the disease severity level caused by cotton aphids. Results of the cotton aphids showed that the proposed approach achieved a grading performance with OA = 0.944, AA = 0.900, and Kappa coefficient = 0.928. Hence, the proposed approach based on hyperspectral index reconstruction is effective and has potential application in grading the aphid infestation severity of cotton.

When communicating between node machines in different locations in the network virtual lab system, the network layer shields the differences of the lower layer networks and cannot provide uniform data transmission of connectionless packets. Aiming at this problem, a self-correcting and optimal scheduling technique for communication networks based on deep machine learning algorithm is proposed. The branching algorithm of the algorithm mainly involves enhancing data learning. By using TCP/IP protocol for communication, a method and program implementation of communication using Socket mechanism under TCP/IP protocol are proposed. System users access the virtual lab primarily through the appropriate browser. The core part of the network virtual lab is server-side communication technology and experimental design. In a virtual lab system, a large number of nodes must be relied on for real-time communication, and the TCP/IP protocol must be followed. The Socket mechanism should be used to implement TCP/IP-based communication. Two breakthroughs were realized, resource scheduling decision and optimization of indirect system parameter selection. The experimental results show that the technical requirements of high throughput and ultra-low latency of the current virtual experimental system are realized.INDEX TERMS Deep machine learning algorithms, TCP/IP protocol, virtual laboratory system, socket communication technology.

No abstract