Moad Idrissi, Ahmad Najiy Wahab, Dalia El-Banna, Da-ming Lai, F. Slik, Taufiq Asyhari
The growth of invasive Acacia Mangium has presented a new biodiversity threat to Brunei, which is situated on the biologically diverse island of Borneo. Hazards to the native flora due to Acacia’s fast invasion and threats to forest fires have resulted in increased risks of burnable oil. In line with Brunei’s National Climate Change Policy, which is reflected in Brunei Vision 2035, it is crucial to conserve Brunei’s extensive forest cover by proactive management of the Acacia population in the country’s tropical rainforests. Therefore, In line with Brunei’s National Climate Change Policy, which is reflected in the Brunei vision, active management of the Acacia population in Brunei’s rainforests is considered crucial as it can determine and scope out the country’s extensive forest cover. In order to identify the species of Acacia tree and the coverage, this study uses UAV-based, high-resolution RGB photos that have been analysed by machine learning software. The images captured are tested and analysed using a convolutional neural network (CNN) model which is trained to detect the Acacia tree species highlighting regions that indicated a maximum accuracy of 84% based on the manually annotated datasets.
{"title":"Digital Detection of Acacia Mangium Trees via Remote Sensing for Controlling the Invasive Population of Biodiversity Threats: Case Study in Brunei","authors":"Moad Idrissi, Ahmad Najiy Wahab, Dalia El-Banna, Da-ming Lai, F. Slik, Taufiq Asyhari","doi":"10.1145/3594692.3594697","DOIUrl":"https://doi.org/10.1145/3594692.3594697","url":null,"abstract":"The growth of invasive Acacia Mangium has presented a new biodiversity threat to Brunei, which is situated on the biologically diverse island of Borneo. Hazards to the native flora due to Acacia’s fast invasion and threats to forest fires have resulted in increased risks of burnable oil. In line with Brunei’s National Climate Change Policy, which is reflected in Brunei Vision 2035, it is crucial to conserve Brunei’s extensive forest cover by proactive management of the Acacia population in the country’s tropical rainforests. Therefore, In line with Brunei’s National Climate Change Policy, which is reflected in the Brunei vision, active management of the Acacia population in Brunei’s rainforests is considered crucial as it can determine and scope out the country’s extensive forest cover. In order to identify the species of Acacia tree and the coverage, this study uses UAV-based, high-resolution RGB photos that have been analysed by machine learning software. The images captured are tested and analysed using a convolutional neural network (CNN) model which is trained to detect the Acacia tree species highlighting regions that indicated a maximum accuracy of 84% based on the manually annotated datasets.","PeriodicalId":207141,"journal":{"name":"Proceedings of the 2023 12th International Conference on Informatics, Environment, Energy and Applications","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127364182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the rapid development of data center, it is urgent to reduce energy consumption from the perspective of central cooling plant. At the same time, with the deepening application of clustering methods in data analysis, this study combines the K-means clustering method in machine learning with the energy consumption simulation software, DeST and applies it to actual case. The weather data of whole year are clustered into 29 typical daily patterns in Changzhou to study the load characteristic. It is found that there are 9 operation modes in the data center. The impact of hourly weather data changes on the external load of the data center is analyzed. The positive and negative impact of the temperature on the load of the following day are 4.96 % and -5.73 % in the heating season, 3.72 % and -2.63 % in the cooling season, which can be ignored. The cooling load of IT equipment accounts for a large proportion while the external load of hot and cold only accounts for 5.02 % and -5.73 % in the data center. Due to its 24-hour operation, the annual load change is relatively stable. The accuracy of load prediction is 56.60 %.
{"title":"Data Center Cooling Load Prediction and Analysis based on Weather Data Clustering","authors":"Huixian Meng, Qingbin Lin, Lun Zhang","doi":"10.1145/3594692.3594693","DOIUrl":"https://doi.org/10.1145/3594692.3594693","url":null,"abstract":"With the rapid development of data center, it is urgent to reduce energy consumption from the perspective of central cooling plant. At the same time, with the deepening application of clustering methods in data analysis, this study combines the K-means clustering method in machine learning with the energy consumption simulation software, DeST and applies it to actual case. The weather data of whole year are clustered into 29 typical daily patterns in Changzhou to study the load characteristic. It is found that there are 9 operation modes in the data center. The impact of hourly weather data changes on the external load of the data center is analyzed. The positive and negative impact of the temperature on the load of the following day are 4.96 % and -5.73 % in the heating season, 3.72 % and -2.63 % in the cooling season, which can be ignored. The cooling load of IT equipment accounts for a large proportion while the external load of hot and cold only accounts for 5.02 % and -5.73 % in the data center. Due to its 24-hour operation, the annual load change is relatively stable. The accuracy of load prediction is 56.60 %.","PeriodicalId":207141,"journal":{"name":"Proceedings of the 2023 12th International Conference on Informatics, Environment, Energy and Applications","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125665142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yuanyuan Lou, Hui Sun, Weijie Wu, Gang Yu, Xiuna Wang
Establishing an accurate and reliable cost measurement model for energy storage plants is an important element in the pre-evaluation of energy storage plants. To this end, a cost measurement method for energy storage plants based on the Grey Wolf algorithm (GWO) optimized Support Vector Machine (SVM) is proposed. Using the GWO algorithm to optimize the penalty factor and kernel function of the SVM, and to establish a cost measurement model for energy storage plants on the basis of the GWO-SVM algorithm. Taking the historical data of storage power plant as an example, the prediction results of the GWO-SVM model are compared with those of SVM, ABC-SVM, CS-SVM and PSO-SVM models. According to the results, GWO-SVM model has a significant effect on improving the measurement accuracy of the cost of energy storage power plants.
{"title":"Electrochemical Energy Storage Plants Costing Study Based on GWO-SVM Algorithm","authors":"Yuanyuan Lou, Hui Sun, Weijie Wu, Gang Yu, Xiuna Wang","doi":"10.1145/3594692.3594703","DOIUrl":"https://doi.org/10.1145/3594692.3594703","url":null,"abstract":"Establishing an accurate and reliable cost measurement model for energy storage plants is an important element in the pre-evaluation of energy storage plants. To this end, a cost measurement method for energy storage plants based on the Grey Wolf algorithm (GWO) optimized Support Vector Machine (SVM) is proposed. Using the GWO algorithm to optimize the penalty factor and kernel function of the SVM, and to establish a cost measurement model for energy storage plants on the basis of the GWO-SVM algorithm. Taking the historical data of storage power plant as an example, the prediction results of the GWO-SVM model are compared with those of SVM, ABC-SVM, CS-SVM and PSO-SVM models. According to the results, GWO-SVM model has a significant effect on improving the measurement accuracy of the cost of energy storage power plants.","PeriodicalId":207141,"journal":{"name":"Proceedings of the 2023 12th International Conference on Informatics, Environment, Energy and Applications","volume":"181 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132454454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chanh Minh Tran, Tho Duc Nguyen, Bach Gia Nguyen, Tan Xuan Phan, E. Kamioka
With the introduction of the novel HTTP/3 prioritization scheme, the video player can conveniently assign a different priority for every download of a video segment in order to allocate suitable bandwidths for them. This work applies such a mechanism to reduce the QoE loss and data wastage of mobile short-form video streaming. Specifically, the proposed method buffers the viewing video and prebuffers (i.e., buffer in advance) pending videos simultaneously with respect to an optimized threshold. Such a threshold is based on an optimization of minimizing the risk of QoE loss caused by playback stalls and the risk of data wastage caused by downloading never-watched content. In order to prevent the prebuffering process from deteriorating the bandwidth of the buffering process, the prebuffering process is assigned the lowest priority and the buffering process is assigned the highest priority. Through evaluation, the proposed method is proven to provide the least QoE loss, data wastage, and a very balanced trade-off between them. Moreover, the crucial role of HTTP/3 prioritization in preventing bandwidth drop and avoiding playback stalls is clearly shown.
{"title":"Reducing QoE Loss and Data Wastage of Short-form Video Streaming with HTTP/3 Prioritization","authors":"Chanh Minh Tran, Tho Duc Nguyen, Bach Gia Nguyen, Tan Xuan Phan, E. Kamioka","doi":"10.1145/3594692.3594741","DOIUrl":"https://doi.org/10.1145/3594692.3594741","url":null,"abstract":"With the introduction of the novel HTTP/3 prioritization scheme, the video player can conveniently assign a different priority for every download of a video segment in order to allocate suitable bandwidths for them. This work applies such a mechanism to reduce the QoE loss and data wastage of mobile short-form video streaming. Specifically, the proposed method buffers the viewing video and prebuffers (i.e., buffer in advance) pending videos simultaneously with respect to an optimized threshold. Such a threshold is based on an optimization of minimizing the risk of QoE loss caused by playback stalls and the risk of data wastage caused by downloading never-watched content. In order to prevent the prebuffering process from deteriorating the bandwidth of the buffering process, the prebuffering process is assigned the lowest priority and the buffering process is assigned the highest priority. Through evaluation, the proposed method is proven to provide the least QoE loss, data wastage, and a very balanced trade-off between them. Moreover, the crucial role of HTTP/3 prioritization in preventing bandwidth drop and avoiding playback stalls is clearly shown.","PeriodicalId":207141,"journal":{"name":"Proceedings of the 2023 12th International Conference on Informatics, Environment, Energy and Applications","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124284745","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
H. R. Shaukat, Bruce Gunn, Michael Johnstone, Doug Creighton
The research contributes to the study of the automated guided vehicle (AGV) utilisation, specifically the number of AGVs involved with different industrial time intervals. Computation of the number of AGVs depends upon the assigned tasks of different time intervals such as loaded and unloaded travel times, loading, and unloading times, return travel, and the completion period. There has been an effort to manage the current research gap in existing studies and help the industry sector to estimate the minimum number of AGVs. Modernisation left an impact on the industry too; this research offers additional knowledge toward the manufacturing sector, particularly how automated guided vehicles can easily deploy with minimum effort, as they are flexible and easily can move on a variety on paths. This research study describes an algorithm for AGV formulation based on the transport time factors, to perform different jobs in any industry. The current COVID pandemic also highlights the importance of robots and digitalisation to compete with such disasters, little effort has been devoted to computing with agent-based simulation, to compare the finding with calculated values. We address the difficulties and demonstrate how many AGVs are required to meet the industry requirement.
{"title":"Computation of Minimum Number of Automated Guided Vehicles (AGVs) with Battery Charging","authors":"H. R. Shaukat, Bruce Gunn, Michael Johnstone, Doug Creighton","doi":"10.1145/3594692.3594706","DOIUrl":"https://doi.org/10.1145/3594692.3594706","url":null,"abstract":"The research contributes to the study of the automated guided vehicle (AGV) utilisation, specifically the number of AGVs involved with different industrial time intervals. Computation of the number of AGVs depends upon the assigned tasks of different time intervals such as loaded and unloaded travel times, loading, and unloading times, return travel, and the completion period. There has been an effort to manage the current research gap in existing studies and help the industry sector to estimate the minimum number of AGVs. Modernisation left an impact on the industry too; this research offers additional knowledge toward the manufacturing sector, particularly how automated guided vehicles can easily deploy with minimum effort, as they are flexible and easily can move on a variety on paths. This research study describes an algorithm for AGV formulation based on the transport time factors, to perform different jobs in any industry. The current COVID pandemic also highlights the importance of robots and digitalisation to compete with such disasters, little effort has been devoted to computing with agent-based simulation, to compare the finding with calculated values. We address the difficulties and demonstrate how many AGVs are required to meet the industry requirement.","PeriodicalId":207141,"journal":{"name":"Proceedings of the 2023 12th International Conference on Informatics, Environment, Energy and Applications","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125152891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Since the carbon reserve of salt marsh vegetation is a key parameter for studying the carbon cycle of coastal wetland ecosystem, it is of great practical significance to study the carbon reserve of multi-species salt marsh vegetation under the background of "carbon peak and carbon neutrality". In this paper, the image of ZhuHai-1 in the core area of Yancheng Wetland Rare Birds National Nature Reserve in Jiangsu, China was taken as the data source. In this paper, Support Vector Machine was used to distinguish vegetation types. Based on PROSAIL radiation transfer model, the forward relationship between vegetation carbon reserve and reflectivity of canopy spectral response was quantitatively analyzed, and the paired data set of the two was constructed. In addition, this paper quantified the relationship between simulated carbon reserve and simulated reflectivity of canopy spectral through neural network model, which was used in the remote sensing image of ZhuHai-1, so as to obtain the spatial and temporal distribution of carbon reserve of salt marsh. According to the statistics, the total carbon reserve of the Spartina alterniflora was 5.74×104 tons, the total carbon reserve of the suaeda was 0.21×104 tons, and the total carbon reserve of the breed was 2.9×104 tons. This study can provide technical support for ecological protection and restoration of coastal salt marshes and carbon sequestration and storage by vegetation.
{"title":"Estimation of Aboveground Vegetation Carbon Storage in Coastal Salt Marshes based on ZhuHai-1 Hyperspectral Satellite Images","authors":"Yue Zou, Huan Li, W. Lin, Jiabao Zhang","doi":"10.1145/3594692.3594696","DOIUrl":"https://doi.org/10.1145/3594692.3594696","url":null,"abstract":"Since the carbon reserve of salt marsh vegetation is a key parameter for studying the carbon cycle of coastal wetland ecosystem, it is of great practical significance to study the carbon reserve of multi-species salt marsh vegetation under the background of \"carbon peak and carbon neutrality\". In this paper, the image of ZhuHai-1 in the core area of Yancheng Wetland Rare Birds National Nature Reserve in Jiangsu, China was taken as the data source. In this paper, Support Vector Machine was used to distinguish vegetation types. Based on PROSAIL radiation transfer model, the forward relationship between vegetation carbon reserve and reflectivity of canopy spectral response was quantitatively analyzed, and the paired data set of the two was constructed. In addition, this paper quantified the relationship between simulated carbon reserve and simulated reflectivity of canopy spectral through neural network model, which was used in the remote sensing image of ZhuHai-1, so as to obtain the spatial and temporal distribution of carbon reserve of salt marsh. According to the statistics, the total carbon reserve of the Spartina alterniflora was 5.74×104 tons, the total carbon reserve of the suaeda was 0.21×104 tons, and the total carbon reserve of the breed was 2.9×104 tons. This study can provide technical support for ecological protection and restoration of coastal salt marshes and carbon sequestration and storage by vegetation.","PeriodicalId":207141,"journal":{"name":"Proceedings of the 2023 12th International Conference on Informatics, Environment, Energy and Applications","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127109813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Traditional approaches often ignore spatial and temporal connections, which cannot match the needs of forecasting assignments due to the extremely nonlinear and complicated nature of traffic flow. In this paper, a novel deep learning model, Efficient Spatiotemporal Graph Convolutional Network (EST-GCN), is proposed to address the time series prediction problem in the transportation domain. EST-GCN is able to jointly capture inter-sequence and temporal correlations through spectral transformation, which is combined with the graph convolutional network (GCN) and the gated linear unit (GLU). The design of the spectral transform enables the model to reduce the computational complexity by using an approximation method while maintaining the prediction accuracy. Furthermore, EST-GCN automatically extracts correlations between sequences from the data without the need of pre-defined prior knowledge. Results show that EST-GCN outperforms state-of-the-art baselines in prediction accuracy and training speed on real-world traffic dataset.
{"title":"An Improved Traffic Forecasting Model based on Efficient Spatiotemporal Graph Convolutional Network","authors":"Bailin Li, Mi Wen","doi":"10.1145/3594692.3594700","DOIUrl":"https://doi.org/10.1145/3594692.3594700","url":null,"abstract":"Traditional approaches often ignore spatial and temporal connections, which cannot match the needs of forecasting assignments due to the extremely nonlinear and complicated nature of traffic flow. In this paper, a novel deep learning model, Efficient Spatiotemporal Graph Convolutional Network (EST-GCN), is proposed to address the time series prediction problem in the transportation domain. EST-GCN is able to jointly capture inter-sequence and temporal correlations through spectral transformation, which is combined with the graph convolutional network (GCN) and the gated linear unit (GLU). The design of the spectral transform enables the model to reduce the computational complexity by using an approximation method while maintaining the prediction accuracy. Furthermore, EST-GCN automatically extracts correlations between sequences from the data without the need of pre-defined prior knowledge. Results show that EST-GCN outperforms state-of-the-art baselines in prediction accuracy and training speed on real-world traffic dataset.","PeriodicalId":207141,"journal":{"name":"Proceedings of the 2023 12th International Conference on Informatics, Environment, Energy and Applications","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126517098","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the significant surge in energy consumption of servers, the data center has begun to extensively adopt air-side economizers for energy saving. However, while the application of air-side economizer brings excellent energy savings, it also has some negative effects, such as the corrosion of electronic equipment. Particulate pollutants are a significant contributor to server corrosion. To clarify the movement patterns of particles in data centers and to better guide the application of air-side economizers, air path flow and concentration distribution simulation of particulate pollutants are carried out in a data center using air-side economizer. Particle sizes utilized for modeling are 0.3 μm and 10 μm respectively. The concentration distribution and airflow path of particles are simulated in the case of cold-aisle containment and hot-aisle containment. The simulation results showed that the average concentration of the entire data center in cold-aisle containment is lower than that of the hot-aisle containment. Based on the theoretical analysis, the Brown force is dominant for 0.3μm and gravity becomes the largest force for 10μm. This explains the sedimentation effect in the 10μm flow trajectory. After obtaining the simulation results, there are several strategies to prevent particle corrosion of the server. Depending on the utilization and importance of the server, the server can be placed accordingly in the area with the lowest predicted amount of particulate pollutants and the best thermal environment. In addition, data center operations and maintenance personnel need to regularly inspect and clean areas with high concentrations of particulate pollutants to prevent server downtime. Another approach is to add barriers to the flow near critical IT equipment to alter the flow path of contaminants leaving the cabinet.
{"title":"Air Path Flow And Concentration Distribution Simulation Of Particulate Pollutants In A Data Center Using Air-side Economizer","authors":"Zuoyang Li, Xuelian Bai","doi":"10.1145/3594692.3594740","DOIUrl":"https://doi.org/10.1145/3594692.3594740","url":null,"abstract":"With the significant surge in energy consumption of servers, the data center has begun to extensively adopt air-side economizers for energy saving. However, while the application of air-side economizer brings excellent energy savings, it also has some negative effects, such as the corrosion of electronic equipment. Particulate pollutants are a significant contributor to server corrosion. To clarify the movement patterns of particles in data centers and to better guide the application of air-side economizers, air path flow and concentration distribution simulation of particulate pollutants are carried out in a data center using air-side economizer. Particle sizes utilized for modeling are 0.3 μm and 10 μm respectively. The concentration distribution and airflow path of particles are simulated in the case of cold-aisle containment and hot-aisle containment. The simulation results showed that the average concentration of the entire data center in cold-aisle containment is lower than that of the hot-aisle containment. Based on the theoretical analysis, the Brown force is dominant for 0.3μm and gravity becomes the largest force for 10μm. This explains the sedimentation effect in the 10μm flow trajectory. After obtaining the simulation results, there are several strategies to prevent particle corrosion of the server. Depending on the utilization and importance of the server, the server can be placed accordingly in the area with the lowest predicted amount of particulate pollutants and the best thermal environment. In addition, data center operations and maintenance personnel need to regularly inspect and clean areas with high concentrations of particulate pollutants to prevent server downtime. Another approach is to add barriers to the flow near critical IT equipment to alter the flow path of contaminants leaving the cabinet.","PeriodicalId":207141,"journal":{"name":"Proceedings of the 2023 12th International Conference on Informatics, Environment, Energy and Applications","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123377261","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Q. Meng, B. Zhu, Chunfeng Zhang, Haoyuan Feng, Xiaohe Yang, Lijun Cai, Zhijia Gai
Based on the analysis of crop growth cycle and water demand, the factors affecting crop growth water use are divided into three categories: environmental factors, crop factors and soil factors. The training set and test set of the model are selected from the crop irrigation historical data set that meets the expected quality and yield. By designing an intelligent farmland irrigation model based on LSTM neural network algorithm, a method of precise irrigation according to crop growth needs, growth environment and planting soil is proposed. According to the characteristics of factors affecting the water consumption for crop growth, the number of hidden layers of the prediction model is determined, and the network parameters are adjusted; The model is trained on the processed historical irrigation data set to obtain the crop irrigation volume prediction model; The LSTM neural network irrigation prediction model is compared with the traditional RNN neural network irrigation prediction model. The experimental results show that the predicted value and trend of LSTM irrigation prediction model are closer to the real value, with stronger robustness, lower error rate and shorter running time, which can meet the prediction of intelligent farmland irrigation and provide reliable basis for the research of intelligent agriculture.
{"title":"Research and Design of Intelligent Farmland Irrigation System Based on Neural Network","authors":"Q. Meng, B. Zhu, Chunfeng Zhang, Haoyuan Feng, Xiaohe Yang, Lijun Cai, Zhijia Gai","doi":"10.1145/3594692.3594704","DOIUrl":"https://doi.org/10.1145/3594692.3594704","url":null,"abstract":"Based on the analysis of crop growth cycle and water demand, the factors affecting crop growth water use are divided into three categories: environmental factors, crop factors and soil factors. The training set and test set of the model are selected from the crop irrigation historical data set that meets the expected quality and yield. By designing an intelligent farmland irrigation model based on LSTM neural network algorithm, a method of precise irrigation according to crop growth needs, growth environment and planting soil is proposed. According to the characteristics of factors affecting the water consumption for crop growth, the number of hidden layers of the prediction model is determined, and the network parameters are adjusted; The model is trained on the processed historical irrigation data set to obtain the crop irrigation volume prediction model; The LSTM neural network irrigation prediction model is compared with the traditional RNN neural network irrigation prediction model. The experimental results show that the predicted value and trend of LSTM irrigation prediction model are closer to the real value, with stronger robustness, lower error rate and shorter running time, which can meet the prediction of intelligent farmland irrigation and provide reliable basis for the research of intelligent agriculture.","PeriodicalId":207141,"journal":{"name":"Proceedings of the 2023 12th International Conference on Informatics, Environment, Energy and Applications","volume":"20 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114020811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the collection and analysis of electricity consumption data, malicious attacks from untrusted third party are prone to incomplete protection of user privacy. However, the periodic and correlation of the electricity consumption data will be ignored with direct random perturbation under local differential privacy, causing the potential for leakage of user life details. Therefore, this paper proposed a mean estimation method for electricity consumption data based on proportion-integral-derivative (PID) and local differential privacy. Firstly, the data was divided into a smooth period and a peak period; Secondly, the classified data was sampled with PID updating the sampling period. Finally, the sampled data was randomly perturbed by the Piecewise Mechanism (PM) and aggregated for mean estimation. The theoretical analysis shows that the method satisfies the local differential privacy. The experimental results demonstrate that the mean estimation error can be controlled within 0.008. As the privacy budget increases, the error becomes smaller and can reach 0.0001 when the privacy budget is maximum with better data utility.
{"title":"Mean estimation of electricity consumption data based on PID and local differential privacy","authors":"Hongjiao Li, Yanli Qin","doi":"10.1145/3594692.3594698","DOIUrl":"https://doi.org/10.1145/3594692.3594698","url":null,"abstract":"In the collection and analysis of electricity consumption data, malicious attacks from untrusted third party are prone to incomplete protection of user privacy. However, the periodic and correlation of the electricity consumption data will be ignored with direct random perturbation under local differential privacy, causing the potential for leakage of user life details. Therefore, this paper proposed a mean estimation method for electricity consumption data based on proportion-integral-derivative (PID) and local differential privacy. Firstly, the data was divided into a smooth period and a peak period; Secondly, the classified data was sampled with PID updating the sampling period. Finally, the sampled data was randomly perturbed by the Piecewise Mechanism (PM) and aggregated for mean estimation. The theoretical analysis shows that the method satisfies the local differential privacy. The experimental results demonstrate that the mean estimation error can be controlled within 0.008. As the privacy budget increases, the error becomes smaller and can reach 0.0001 when the privacy budget is maximum with better data utility.","PeriodicalId":207141,"journal":{"name":"Proceedings of the 2023 12th International Conference on Informatics, Environment, Energy and Applications","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114634645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：