scispace - formally typeset
Search or ask a question
Author

Hao Zhong

Bio: Hao Zhong is an academic researcher from Guilin University of Electronic Technology. The author has contributed to research in topics: Population & Environmental pollution. The author has an hindex of 1, co-authored 6 publications receiving 6 citations.

Papers
More filters
Patent
23 Feb 2018
TL;DR: In this article, an internet-of-things based crop pest intelligent predicting and forecasting system is presented, which can realize real-time prediction and forecast under a wide-area environment, is favorable for improving crop pest occurrence and damage prediction and forecasting intelligence and accuracy.
Abstract: The invention discloses an internet-of-things based crop pest intelligent predicting and forecasting system. The internet-of-things based crop pest intelligent predicting and forecasting system feedsback survey data to a monitoring center to perform analysis through internet-of-things image identification, remote monitoring, transmission and control technologies on the basis of inheriting the traditional crop pest predicting and forecasting habit and experience, and a crop pest intelligent predicting and forecasting device is constructed; and the dynamic evolution process of pest population generation and development is acquired timely, and prediction and forecast accuracy and timeliness are improved. The internet-of-things based crop pest intelligent predicting and forecasting system realizes unattended intelligent monitoring, can realize real-time prediction and forecast under a wide-area environment, is favorable for improving crop pest occurrence and damage predicting and forecasting intelligence and accuracy, monitors and forecasts the dynamic condition of the population timely, takes measures to control pest damage, and reduces the application amount of pesticide and environmental pollution.

4 citations

Journal ArticleDOI
TL;DR: Based on the calculation process of the three indexes, the paper proposes new three indexes NSC, NDBI and NCHI that can better evaluate clustering results.
Abstract: Clustering algorithm is the main field in collaborative computing of social network. How to evaluate clustering results accurately has become a hot spot in clustering algorithm research. Commonly used evaluation indexes are SC, DBI and CHI. There are two shortcomings in the calculation of three indexes. (1) Keep the number of clusters and the objects in the cluster unchanged. When transforming the feature vector, the three indexes will change greatly; (2) Keep the feature vector and the number of clusters unchanged. When changing the objects in the cluster, the three indexes will change tinily. This shows that the three indexes unable to evaluate the clustering results very well. Therefore, based on the calculation process of the three indexes, the paper proposes new three indexes - NSC, NDBI and NCHI. Through testing on standard data sets, three new indexes can better evaluate clustering results.

3 citations

Journal ArticleDOI
TL;DR: The paper optimizes the rating prediction task from the perspectives of data processing and the prediction model, which reduces the error of the ratings prediction while achieving cross-platform rating predictions.

2 citations

Patent
26 Jun 2018
TL;DR: In this article, the utility model discloses a crops pest intelligence forecasting system based on thing networking, it will investigate data feedback through thing networking image recognition, remote monitoring,transmission and control technique and carry out the analysis to the monitoring center on the basis of custom and experience is observeded and predict to the traditional crops pest of succession, and the device is observede and predict, in time acquireing the pest population and taking place the dynamic development process of development, the accuracy that promotes the prediction forecast is with ageing.
Abstract: The utility model discloses a crops pest intelligence forecasting system based on thing networking, it will be investigated data feedback through thing networking image recognition, remote monitoring,transmission and control technique and carry out the analysis to the monitoring center on the basis of custom and experience is observeded and predict to the traditional crops pest of succession, andthe device is observeded and predict to structure crops pest intelligence, in time acquireing the pest population and taking place the dynamic development process of development, the accuracy that promotes the prediction forecast is with ageing. The utility model discloses unmanned on duty's intellectualized supervisory control has not only been realized, observinging and predicting in real timeunder the wide area environment can be realized, and helping improving the intelligent and accuracy that harm prediction forecast is taken place to the crops pest, monitoring in time and the harm thatits population dynamics of forecast helps scientific and reasonable to take measures to control this worm reduce applications of pesticide volume and environmental pollution.

1 citations

Journal ArticleDOI
13 Jul 2018
TL;DR: The experimental results show that the method proposed in this paper can improve the prediction error to a certain extent.
Abstract: Linear models are common prediction models in collaborative computing, which mainly generates fitting function to express the relationship between feature vectors and predictive value. In the process of computing the predictive value according to the fitting function and feature vector, this paper mainly conducted the following researches. Firstly, this paper defines a change interval of predictive value according to training set. Secondly, in this paper, the change interval of predictive value corresponding to feature vector in test set is computed. Finally, according to distribution of training set in the changing interval, the predictive values corresponding to feature vectors in test set are computed. Standard data sets are used in experiment, and MAE(Mean Absolute Error) and RMSE(Root Mean Square Error) are used to evaluate the prediction results. The experimental results show that the method proposed in this paper can improve the prediction error to a certain extent. Received on 07 June 2020; accepted on 23 September 2020; published on 02 October 2020

Cited by
More filters
Journal ArticleDOI
TL;DR: Wang et al. as discussed by the authors proposed a carbon emission prediction model based on the improved whale algorithm-optimized gradient boosting decision tree, which combines four optimization methods and significantly improves the prediction accuracy.
Abstract: As the global temperature continues to rise, people have become increasingly concerned about global climate change. In order to help China to effectively develop a carbon peak target completion plan, this paper proposes a carbon emission prediction model based on the improved whale algorithm-optimized gradient boosting decision tree, which combines four optimization methods and significantly improves the prediction accuracy. This paper uses historical data to verify the superiority of the gradient boosting tree prediction model optimized by the improved whale algorithm. In addition, this study also predicted the carbon emission values of China from 2020 to 2035 and compared them with the target values, concluding that China can accomplish the relevant target values, which suggests that this research has practical implications for China’s future carbon emission reduction policies.

8 citations

Journal ArticleDOI
TL;DR: In this article , the concordance between regional functions and mobility features was evaluated with datasets of dockless bike-sharing (DBS) usage and land use near metro stations.

4 citations

Patent
04 Jun 2019
TL;DR: In this paper, a standard growth model is built by comparing with a plant growth library according to the type of a plant planted by a user in a signing area and the current growth period.
Abstract: The invention relates to the technical field of agricultural Internet, in particular to a pest and disease identification method and device, and the method comprises the steps: building a standard growth model by comparing with a plant growth library according to the type of a plant planted by a user in a signing area and the current growth period; Obtaining actual data of each growth index of theplant in the signed area, matching the actual data with the standard growth model, and further judging the growth state of the plant; When it is determined that the plant is in the pest and disease damage state, carrying out image collection in the contract signing area, and determining and pushing the pest and disease damage types by combining image recognition and a pest and disease damage database to an intelligent terminal. The plant detail index database is established in advance, the plant growth state can be accurately monitored by matching the obtained actual data with the corresponding standard data, the pest and disease occurrence degree is determined, the pest and disease type can be further determined through image recognition, and a user can know the pest and disease type timely, rapidly and accurately.

3 citations

Patent
07 May 2019
TL;DR: In this article, a pest recognition early warning method and device based on multiple characteristics is proposed, and the method comprises the steps: carrying out the induction capture of insects, collecting corresponding insect recognition characteristics, and determining the types of the insects through the weighted analysis of different insects recognition characteristics; judging whether insects are pests or not according to the insect types and the plant types, and updating the corresponding pest indexes if the insects are the pests; Obtaining environment characteristics, determining the insect pest grade through comprehensive analysis of the insect index and the environment characteristics.
Abstract: The invention relates to the technical field of agricultural Internet, in particular to a pest recognition early warning method and device based on multiple characteristics, and the method comprises the steps: carrying out the induction capture of insects, collecting corresponding insect recognition characteristics, and determining the types of the insects through the weighted analysis of different insect recognition characteristics; Judging whether insects are pests or not according to the insect types and the plant types of the farmland, and updating the corresponding pest indexes if the insects are the pests; Obtaining environment characteristics, determining the insect pest grade through comprehensive analysis of the insect pest index and the environment characteristics, and sending out corresponding early warning according to the insect pest grade. According to the method, firstly, insects are captured, multi-dimensional characteristics such as insect pictures, wing vibration frequencies and plant pictures are more conveniently collected to identify insect types, and identification is more accurate and reliable; Meanwhile, through combination of multi-dimensional features of insect features and environment features, insect pest grades are accurately recognized, early warning is conducted, the insect pest recognition accuracy is improved, and insect pest early warning is more intelligent and reliable.

2 citations

Journal ArticleDOI
TL;DR: The color segmentation algorithm combining the self-organizing maps neural network and the efficient dense subspace clustering was proposed and results show that the algorithm can recognize the color of small areas accurately and segment the colour of complex printed fabric images.
Abstract: In order to achieve accurate color segmentation of printed fabrics, the color segmentation algorithm combining the self-organizing maps neural network and the efficient dense subspace clustering was proposed in this paper. After pre-processing of the fabric image, the primary clustering was implemented by the self-organizing maps algorithm, then the secondary clustering was done by the efficient dense subspace clustering algorithm. The optimal silhouette coefficient is introduced into the clustering process of the efficient dense subspace clustering algorithm to determine the number of clustering centers automatically. Finally, by the post-processing including gray-scale transformation, binarization and open operation, the mis-segmentation of edge color was eliminated, making the algorithm more suitable for industrial application. Experiments were carried out and results show that the algorithm proposed in this paper can recognize the color of small areas accurately and segment the color of complex printed fabric images. The color segmented results of 20 printed fabrics show that the accuracy of the algorithm proposed in this paper reaches 88.3%.

1 citations