Search

The traditional method of detecting crop nutrients is based on the direct chemical detection method in the laboratory, which causes great damage to crops. In order to solve the above problems, the main goal of this study is to design a precise fertilization method for greenhouse vegetables based on the improved back-propagation neural network (IM-BPNN) algorithm to increase fertilizer utilization efficiency, reduce production costs, and improve the economic viability of agriculture. First, soil samples from the farm in china are selected. With the laboratory treatment, available phosphorus, available potassium, and alkaline nitrogen are extracted. These data are preprocessed by the z-score (zero-mean normalization) standardization method. Then, the BPNN (backpropagation neural network) algorithm is improved by being trained and combined with the characteristics of the dual particle swarm optimization algorithm. After that, the soil sample data are divided into training and test sets, and the model is established by setting parameters, weights, and network hierarchy. Finally, the NBTY (nutrient balance target yield),BPNN (backpropagation neural network) and IM-BPNN algorithm are used to calculate the amount of fertilizer. Compared with the BPNN and NBTY algorithm, it shows that the IM-BPNN algorithm can more accurately determine the amount of fertilizer required by vegetables and avoid over-application, which can improve fertilizer utilization efficiency, reduce production costs, and improve the economic feasibility of agriculture. [ABSTRACT FROM AUTHOR]

The agricultural WSN (wireless sensor network) has the characteristics of long operation cycle and wide coverage area. In order to cover as much area as possible, farms usually deploy multiple monitoring devices in different locations of the same area. Due to different types of equipment, monitoring data will vary greatly, and too many monitoring nodes also reduce the efficiency of the network. Although there have been some studies on data fusion algorithms, they have problems such as ignoring the dynamic changes of time series, weak anti-interference ability, and poor processing of data fluctuations. So in this study, a data fusion algorithm for optimal node tracking in agricultural wireless sensor networks is designed. By introducing the dynamic bending distance in the dynamic time warping algorithm to replace the absolute distance in the fuzzy association algorithm and combine the sensor's own reliability and association degree as the weighted fusion weight, which improved the fuzzy association algorithm. Finally, another three algorithm were tested for multi-temperature sensor data fusion. Compare with the kalman filter, arithmetic mean and fuzzy association algorithm, the average value of the improved data fusion algorithm is 29.5703, which is close to the average value of the other three algorithms, indicating that the data distribution is more even. Its extremely bad value is 8.9767, which is 10.04%, 1.14% and 9.85% smaller than the other three algorithms, indicating that it is more robust when dealing with outliers. Its variance is 2.6438, which is 2.82%, 0.65% and 0.27% smaller than the other three algorithms, indicating that it is more stable and has less data volatility. The results show that the algorithm proposed in this study has higher fusion accuracy and better robustness, which can obtain the fusion value that truly feedbacks the agricultural environment conditions. It reduces production costs by reducing redundant monitoring devices, the energy consumption and improves the data collection efficiency in wireless sensor networks. [ABSTRACT FROM AUTHOR]

With the rapid growth of the agricultural information and the need for data analysis, how to accurately extract useful information from massive data has become an urgent first step in agricultural data mining and application. In this study, an agricultural question-answering information extraction method based on the BE-BILSTM (Improved Bidirectional Long Short-Term Memory) algorithm is designed. Firstly, it uses Python's Scrapy crawler framework to obtain the information of soil types, crop diseases and pests, and agricultural trade information, and remove abnormal values. Secondly, the information extraction converts the semi-structured data by using entity extraction methods. Thirdly, the BERT (Bidirectional Encoder Representations from Transformers) algorithm is introduced to improve the performance of the BILSTM algorithm. After comparing with the BERT-CRF (Conditional Random Field) and BILSTM algorithm, the result shows that the BE-BILSTM algorithm has better information extraction performance than the other two algorithms. This study improves the accuracy of the agricultural information recommendation system from the perspective of information extraction. Compared with other work that is done from the perspective of recommendation algorithm optimization, it is more innovative; it helps to understand the semantics and contextual relationships in agricultural question and answer, which improves the accuracy of agricultural information recommendation systems. By gaining a deeper understanding of farmers' needs and interests, the system can better recommend relevant and practical information. [ABSTRACT FROM AUTHOR]

Network reconfiguration is a process to change the open-switches in distribution system for a minimum power loss. In the past, metaheuristic techniques were applied widely for network reconfiguration with consideration of a fixed loading profile. When the loading changes, the current configuration may not be the optimal one. Thus, the technique needs to be executed to find a new optimal configuration based on the latest loading. The process is time-consuming since metaheuristic techniques commonly require high computational times and produces inconsistent results. Therefore, this paper proposes a network reconfiguration technique based on artificial neural network (ANN) for variable loading conditions. The proposed ANN model is tested on IEEE 33-bus, IEEE 69-bus, and IEEE-118 bus systems. The test results indicate the efficiency of the proposed technique in three aspects: processing time, simple structure, and high accuracy. [ABSTRACT FROM AUTHOR]

In mobile ad hoc networks, limited energy resources and traffic congestion at the nodes are crucial issues due to the nodes being battery operated and flooding the network with packets, respectively. These issues degrade network routing performance in terms of quality of service. In this study, we proposed a contention window and residual battery-aware multipath routing scheme to enhance network performance. Our proposed routing scheme has successfully diverted the traffic load from a low energy node to a high energy node while also controlling congestion among intermediate nodes. A multi-criteria decision-making technique was also used for the selection criteria of an intermediate node in the optimal path, based on the mobility and window size contention of nodes. Eventually, the contention window and residual battery-aware multipath routing scheme has enhanced throughput, attenuated the packet loss ratio, and reduced the energy consumption in comparison to a conventional multipath optimized link state routing protocol routing scheme. [ABSTRACT FROM AUTHOR]

In order to resolve the issue of coverage limitation for the future fifth-generation network, deploying a relay node within a cell is one of the most capable and cost-effective solution, which not only enhances the coverage but also improves the spectral efficiency. However, this solution leads to the undesired interferences from nearby base station and relay nodes that affects user's signal-to-interference-plus-noise ratio and can cause the ambiguous received signal at the user end. In this article, we have analyzed a relay-based interference-limited network at millimeter wave frequency and proposed a Poisson point process-based model using a stochastic geometrical approach. The results for the proposed Poisson point process model have been evaluated in terms of success probability, network ergodic capacity, and outage probability, compared with the ideal grid model and conventional multiple-antenna ultra-dense network model. The results proved that the success probability and ergodic capacity for the proposed model are 3.5% and 2.3% higher as compared to the most commonly used model for the high-density network, respectively. Furthermore, the results have been analyzed at different multiple-input-multiple-output antenna configuration, which validates the model in the improvement of overall network performance even for higher number of antennas. [ABSTRACT FROM AUTHOR]