In order to study the semantic detection accuracy of 3D vehicle accident video, an accident detection method combining 2D image and 3D information was proposed. The 3D semantic bounding box generated by the 3D detection and tracking task of the vehicle is used to extract the motion features of the vehicle, it includes the trajectory of the vehicle and the dimension and orientation of the 3D bounding frame, and the 3D semantic bounding frame is used to establish the evaluation index of the accident detection. The experimental results show that the average loss function of each batch of 1000 images is calculated by the stochastic gradient descent method to update the parameter values. The learning rate was set to 0.001 in the first 30,000 iterations and 0.0001 in the last 10,000 iterations. The MOTA of the CEM algorithm is 78.4%, FP is 1.1%, and FN is 3.5%, and the MOTA of the 3-DCMK algorithm is 88.6%, FP is 0.9%, and FN is 1.9%. The MOTA of this method is 89.3%, FP is 0.9%, and FN is 1.2%. The 3D target semantic detection of vehicle accident video has stability and accuracy.
{"title":"Semantic Detection of Vehicle Violation Video Based on Computer 3D Vision","authors":"Yue Dai","doi":"10.1155/2022/5283191","DOIUrl":"https://doi.org/10.1155/2022/5283191","url":null,"abstract":"In order to study the semantic detection accuracy of 3D vehicle accident video, an accident detection method combining 2D image and 3D information was proposed. The 3D semantic bounding box generated by the 3D detection and tracking task of the vehicle is used to extract the motion features of the vehicle, it includes the trajectory of the vehicle and the dimension and orientation of the 3D bounding frame, and the 3D semantic bounding frame is used to establish the evaluation index of the accident detection. The experimental results show that the average loss function of each batch of 1000 images is calculated by the stochastic gradient descent method to update the parameter values. The learning rate was set to 0.001 in the first 30,000 iterations and 0.0001 in the last 10,000 iterations. The MOTA of the CEM algorithm is 78.4%, FP is 1.1%, and FN is 3.5%, and the MOTA of the 3-DCMK algorithm is 88.6%, FP is 0.9%, and FN is 1.9%. The MOTA of this method is 89.3%, FP is 0.9%, and FN is 1.2%. The 3D target semantic detection of vehicle accident video has stability and accuracy.","PeriodicalId":415473,"journal":{"name":"Adv. Multim.","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115771825","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 rise and development of precision agriculture and smart agriculture concepts, traditional agricultural pest detection and identification methods have become increasingly unable to meet current agricultural production requirements due to their slow recognition speed, low recognition accuracy, and strong subjectivity need. This article aims to combine multifeature fusion technology with sensors to apply to crop pest detection and build crop pest detection services based on image recognition. In terms of image recognition, the use of image denoising methods based on median filtering, image preprocessing methods based on the maximum between-class error method (Otsu), image segmentation methods based on super green features, and feature extraction methods based on multiparameter features and based on the one-to-one elimination strategy and the M-SVM multiclass recognition algorithm fused with the kernel function, it realizes the identification and detection of six soybean leaf borers. The system uses the ARM920T series S3C2440 chip as the central processing unit. Through the temperature and humidity sensor and infrared, the multisensor module composed of sensors collects real-time information on the agricultural greenhouse. After normalizing the information, the central processing unit performs judgment processing and information fusion. And through experimental data, it is finally verified that the image recognition method used in this paper improves the recognition rate and effectiveness by nearly 65% in the detection of soybean leaf moth pests.
{"title":"Image Recognition Method of Agricultural Pests Based on Multisensor Image Fusion Technology","authors":"Xianfeng Zeng, Changjiang Huang, Liuchun Zhan","doi":"10.1155/2022/6359130","DOIUrl":"https://doi.org/10.1155/2022/6359130","url":null,"abstract":"With the rise and development of precision agriculture and smart agriculture concepts, traditional agricultural pest detection and identification methods have become increasingly unable to meet current agricultural production requirements due to their slow recognition speed, low recognition accuracy, and strong subjectivity need. This article aims to combine multifeature fusion technology with sensors to apply to crop pest detection and build crop pest detection services based on image recognition. In terms of image recognition, the use of image denoising methods based on median filtering, image preprocessing methods based on the maximum between-class error method (Otsu), image segmentation methods based on super green features, and feature extraction methods based on multiparameter features and based on the one-to-one elimination strategy and the M-SVM multiclass recognition algorithm fused with the kernel function, it realizes the identification and detection of six soybean leaf borers. The system uses the ARM920T series S3C2440 chip as the central processing unit. Through the temperature and humidity sensor and infrared, the multisensor module composed of sensors collects real-time information on the agricultural greenhouse. After normalizing the information, the central processing unit performs judgment processing and information fusion. And through experimental data, it is finally verified that the image recognition method used in this paper improves the recognition rate and effectiveness by nearly 65% in the detection of soybean leaf moth pests.","PeriodicalId":415473,"journal":{"name":"Adv. Multim.","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131989072","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 order to improve the cooperative operation scheduling effect of agricultural machinery, this article uses particle swarm neural network to study the cooperative operation scheduling algorithm of agricultural machinery and improves the cooperative scheduling effect of intelligent agricultural machinery. Aiming at the mixed integer nonlinear programming problem, this article proposes a collaborative algorithm of population intelligence and linear programming. The outer layer of the algorithm uses the improved particle swarm algorithm IPSO module, the inner layer uses the simplex algorithm SIM module, and the optimal solution of the MINLP problem is obtained through the iterative update of the inner and outer modules. The experimental study shows that the cooperative operation scheduling model of agricultural machinery based on particle swarm neural network proposed in this article can play an important role in modern agricultural planting and effectively improve the efficiency of agricultural planting.
{"title":"Research on Scheduling Algorithm of Agricultural Machinery Cooperative Operation Based on Particle Swarm Neural Network","authors":"Wei Li","doi":"10.1155/2022/1231642","DOIUrl":"https://doi.org/10.1155/2022/1231642","url":null,"abstract":"In order to improve the cooperative operation scheduling effect of agricultural machinery, this article uses particle swarm neural network to study the cooperative operation scheduling algorithm of agricultural machinery and improves the cooperative scheduling effect of intelligent agricultural machinery. Aiming at the mixed integer nonlinear programming problem, this article proposes a collaborative algorithm of population intelligence and linear programming. The outer layer of the algorithm uses the improved particle swarm algorithm IPSO module, the inner layer uses the simplex algorithm SIM module, and the optimal solution of the MINLP problem is obtained through the iterative update of the inner and outer modules. The experimental study shows that the cooperative operation scheduling model of agricultural machinery based on particle swarm neural network proposed in this article can play an important role in modern agricultural planting and effectively improve the efficiency of agricultural planting.","PeriodicalId":415473,"journal":{"name":"Adv. Multim.","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123686394","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}
As a common method of deep learning, a convolutional neural network (CNN) shows excellent performance in face recognition. The features extracted by traditional face recognition methods are greatly influenced by subjective factors and are time-consuming and laborious. In addition, these images are susceptible to illumination, expression, occlusion, posture, and other factors, which bring a lot of interference to the computer face recognition and increase recognition difficulty. Deep learning is the most important technical means in the field of computer vision. The participation of this technology reduces manual participation and can identify the identity of visitors from multiple aspects. This study, based on the introduction at all levels and on the fundamental principle of the colloidal neural network, combines the basic model and the common exploitation methods of aspects to make a model of a combination of multiple aspects. Then, an improved CNN-based multifeature fusion face recognition model is proposed, and the effectiveness of the model in face feature extraction is verified by experiments. With the experimental results, the identification rate for the ORL and Yale data sets is 98.2% and 98.8%, respectively. Accordingly, an online face detection system and recognition system based on the combination of element models are designed. The system can obtain dynamic facial recognition and meet the recognition rate of the design requirements. The system is training four detection models and online recognition, and the test results show that the noise component model has the highest recognition rate, and the recognition rate has improved by 13% compared with the baseline capacity, further verifying that a model of a combination of features can achieve more effectively.
{"title":"Deblurring Method of Face Recognition AI Technology Based on Deep Learning","authors":"Weilong Li, J. Li, Junhui Zhou","doi":"10.1155/2022/9146711","DOIUrl":"https://doi.org/10.1155/2022/9146711","url":null,"abstract":"As a common method of deep learning, a convolutional neural network (CNN) shows excellent performance in face recognition. The features extracted by traditional face recognition methods are greatly influenced by subjective factors and are time-consuming and laborious. In addition, these images are susceptible to illumination, expression, occlusion, posture, and other factors, which bring a lot of interference to the computer face recognition and increase recognition difficulty. Deep learning is the most important technical means in the field of computer vision. The participation of this technology reduces manual participation and can identify the identity of visitors from multiple aspects. This study, based on the introduction at all levels and on the fundamental principle of the colloidal neural network, combines the basic model and the common exploitation methods of aspects to make a model of a combination of multiple aspects. Then, an improved CNN-based multifeature fusion face recognition model is proposed, and the effectiveness of the model in face feature extraction is verified by experiments. With the experimental results, the identification rate for the ORL and Yale data sets is 98.2% and 98.8%, respectively. Accordingly, an online face detection system and recognition system based on the combination of element models are designed. The system can obtain dynamic facial recognition and meet the recognition rate of the design requirements. The system is training four detection models and online recognition, and the test results show that the noise component model has the highest recognition rate, and the recognition rate has improved by 13% compared with the baseline capacity, further verifying that a model of a combination of features can achieve more effectively.","PeriodicalId":415473,"journal":{"name":"Adv. Multim.","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126184374","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}
The objective of this paper is to optimize the scene of tourism virtual perception space. Based on the abstract method of semantic feature points, the computing model of semantic perception of single-cultural landscape and multi-cultural landscape is established. Using the digital elevation model, an empirical study on the semantic perception of cultural landscape in the western Tombs of Qing Dynasty is carried out. Taking the traditional Chinese culture of the site selection of royal tombs and the feudal hierarchy represented as the semantic criteria, eighteen feature points were extracted from two representative tomb cultural landscapes from different landscape perspectives, and the corresponding weight coefficients were assigned to each feature point from different landscape perspectives; based on the results of perceptual degree calculation, the semantic mining of the existing sightseeing routes is carried out and the optimization scheme is designed. From the perspective of tourists’ perception of landscape, tourism resources are deeply mined to better reflect the value of landscape and realize the coupling and interaction between virtual tourism and tourism economy.
{"title":"Research on Optimization of 3D Tourism Virtual Crossover Scene based on Semantic Perception Analysis","authors":"Guixia Wang","doi":"10.1155/2022/9721570","DOIUrl":"https://doi.org/10.1155/2022/9721570","url":null,"abstract":"The objective of this paper is to optimize the scene of tourism virtual perception space. Based on the abstract method of semantic feature points, the computing model of semantic perception of single-cultural landscape and multi-cultural landscape is established. Using the digital elevation model, an empirical study on the semantic perception of cultural landscape in the western Tombs of Qing Dynasty is carried out. Taking the traditional Chinese culture of the site selection of royal tombs and the feudal hierarchy represented as the semantic criteria, eighteen feature points were extracted from two representative tomb cultural landscapes from different landscape perspectives, and the corresponding weight coefficients were assigned to each feature point from different landscape perspectives; based on the results of perceptual degree calculation, the semantic mining of the existing sightseeing routes is carried out and the optimization scheme is designed. From the perspective of tourists’ perception of landscape, tourism resources are deeply mined to better reflect the value of landscape and realize the coupling and interaction between virtual tourism and tourism economy.","PeriodicalId":415473,"journal":{"name":"Adv. Multim.","volume":"80 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130723072","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 wireless sensor networks (WSNs), aiming at the problems that internal attacks such as network congestion and high energy consumption seriously threaten the network security and normal operation, an intrusion detection technology based on traffic prediction is proposed. Firstly, the technology uses the autoregressive moving average model ARMA (autoregressive moving average) to establish the ARMA traffic prediction model for the node and then uses the predicted traffic value to obtain the traffic reception rate range through the node. Finally, the detection effect is achieved by comparing whether the actual service reception rate exceeds the prediction range. The experimental results show that, compared with the single ARMA model, under the same message playback rate, this technology has higher detection rate and lower false alarm rate and reduces the energy consumption of network nodes.
{"title":"Intrusion Detection Technology for Wireless Sensor Networks Based on Autoregressive Moving Average","authors":"Julian Yu","doi":"10.1155/2022/2155748","DOIUrl":"https://doi.org/10.1155/2022/2155748","url":null,"abstract":"In wireless sensor networks (WSNs), aiming at the problems that internal attacks such as network congestion and high energy consumption seriously threaten the network security and normal operation, an intrusion detection technology based on traffic prediction is proposed. Firstly, the technology uses the autoregressive moving average model ARMA (autoregressive moving average) to establish the ARMA traffic prediction model for the node and then uses the predicted traffic value to obtain the traffic reception rate range through the node. Finally, the detection effect is achieved by comparing whether the actual service reception rate exceeds the prediction range. The experimental results show that, compared with the single ARMA model, under the same message playback rate, this technology has higher detection rate and lower false alarm rate and reduces the energy consumption of network nodes.","PeriodicalId":415473,"journal":{"name":"Adv. Multim.","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126892992","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}
Because the traditional GDP accounting method was difficult to meet the actual needs of governments for economic and social development, aiming at the problems of unclear data sources related to GDP and inconsistent GDP accounting results in the national economic accounting system, a GDP index financial accounting method based on numerical simulation was proposed. Firstly, it summarized the traditional GDP thought and its related accounting methods and analyzed the common problems existing in the traditional GDP accounting. Secondly, it expounded the concept of green GDP and its accounting scope and theoretical model and pointed out the key problems to be solved in green GDP accounting, such as ecological resource consumption and environmental pollution cost calculation. Finally, by analyzing the relationship between green GDP and main supporting indicators, the accounting method of GDP indicators based on numerical simulation was proposed, and the accounting result detection model based on the econometric model was given. Through empirical analysis, it showed that the GDP accounting method proposed in this paper has good feasibility and effectiveness and can effectively reflect the development of the economic operation. The accounting method proposed in this paper can also provide a reference basis for the construction of a green GDP system.
{"title":"Research on Financial Accounting of GDP Index Based on Numerical Simulation","authors":"Bo Li","doi":"10.1155/2022/2386789","DOIUrl":"https://doi.org/10.1155/2022/2386789","url":null,"abstract":"Because the traditional GDP accounting method was difficult to meet the actual needs of governments for economic and social development, aiming at the problems of unclear data sources related to GDP and inconsistent GDP accounting results in the national economic accounting system, a GDP index financial accounting method based on numerical simulation was proposed. Firstly, it summarized the traditional GDP thought and its related accounting methods and analyzed the common problems existing in the traditional GDP accounting. Secondly, it expounded the concept of green GDP and its accounting scope and theoretical model and pointed out the key problems to be solved in green GDP accounting, such as ecological resource consumption and environmental pollution cost calculation. Finally, by analyzing the relationship between green GDP and main supporting indicators, the accounting method of GDP indicators based on numerical simulation was proposed, and the accounting result detection model based on the econometric model was given. Through empirical analysis, it showed that the GDP accounting method proposed in this paper has good feasibility and effectiveness and can effectively reflect the development of the economic operation. The accounting method proposed in this paper can also provide a reference basis for the construction of a green GDP system.","PeriodicalId":415473,"journal":{"name":"Adv. Multim.","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127744274","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 order to analyze e-commerce customer behavior and preference, a migration identification method of consumer behavior tendency is proposed. Data mining technology is adopted to mine social data in individual online we-media platforms and to mine individual personal attributes and preferences from their unconscious social language. Its methods are through the customer identification model construction related research, consumer preference identification and analysis related research, based on data mining technology of consumer preference identification and analysis, and the introduction of feature extraction method: semantic analysis. According to the data, there are 2,990 customer interest consumption forecasts, 1,836 customer social network data consumption forecasts, and 3,652 customer preference consumption forecasts. In order to screen out the main factors that have the greatest impact on consumer behavior from all kinds of consumer behavior propensity factors, the multiple step-based regression method is adopted for factor selection. Because of the large difference in the multidimensional dynamic vector, the corresponding consumer behavior tendency changes greatly, so the migration identification method of consumer behavior tendency is feasible.
{"title":"Research on E-Commerce Customer Feature Extraction Question Answering System Based on Artificial Intelligence Semantic Analysis","authors":"W. Niu","doi":"10.1155/2022/6934194","DOIUrl":"https://doi.org/10.1155/2022/6934194","url":null,"abstract":"In order to analyze e-commerce customer behavior and preference, a migration identification method of consumer behavior tendency is proposed. Data mining technology is adopted to mine social data in individual online we-media platforms and to mine individual personal attributes and preferences from their unconscious social language. Its methods are through the customer identification model construction related research, consumer preference identification and analysis related research, based on data mining technology of consumer preference identification and analysis, and the introduction of feature extraction method: semantic analysis. According to the data, there are 2,990 customer interest consumption forecasts, 1,836 customer social network data consumption forecasts, and 3,652 customer preference consumption forecasts. In order to screen out the main factors that have the greatest impact on consumer behavior from all kinds of consumer behavior propensity factors, the multiple step-based regression method is adopted for factor selection. Because of the large difference in the multidimensional dynamic vector, the corresponding consumer behavior tendency changes greatly, so the migration identification method of consumer behavior tendency is feasible.","PeriodicalId":415473,"journal":{"name":"Adv. Multim.","volume":"160 8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116925739","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 order to study the current intelligent home pension system control technology, the new voice interaction technology is applied to the existing intelligent home pension system, and a multicontrol entry intelligent home pension system method is proposed. In this method, data transmission, instruction uploading, and receiving are completed by designing the communication interface of home appliance terminal to build the wireless intelligent home communication subsystem, and the voice module of IfI is adopted. The intelligent cloud is selected as the development cloud platform, and the related hardware is selected to realize the remote data communication. It has been proved that the key technology of speech recognition has been developed rapidly, the speech recognition rate has been improved (up to 97%) and the low-power speech wake up technology had breakthrough, the use of voice interaction is gradually expanding to intelligent hardware and robots, and voice interaction is undoubtedly the mainstream intelligent home pension system interaction mode after keyboard, mouse, and touch screen and also the main entrance of the future intelligent home pension system.
{"title":"Research and Implementation of Intelligent Home Pension System Based on Speech and Semantic Recognition","authors":"Guokun Xie, Sen Hao, Peipei Zhang, Ningning Wang","doi":"10.1155/2022/6141295","DOIUrl":"https://doi.org/10.1155/2022/6141295","url":null,"abstract":"In order to study the current intelligent home pension system control technology, the new voice interaction technology is applied to the existing intelligent home pension system, and a multicontrol entry intelligent home pension system method is proposed. In this method, data transmission, instruction uploading, and receiving are completed by designing the communication interface of home appliance terminal to build the wireless intelligent home communication subsystem, and the voice module of IfI is adopted. The intelligent cloud is selected as the development cloud platform, and the related hardware is selected to realize the remote data communication. It has been proved that the key technology of speech recognition has been developed rapidly, the speech recognition rate has been improved (up to 97%) and the low-power speech wake up technology had breakthrough, the use of voice interaction is gradually expanding to intelligent hardware and robots, and voice interaction is undoubtedly the mainstream intelligent home pension system interaction mode after keyboard, mouse, and touch screen and also the main entrance of the future intelligent home pension system.","PeriodicalId":415473,"journal":{"name":"Adv. Multim.","volume":"400-402 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132024650","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 order to study the recommendation system of digital media based on semantic classification, the CF-LFMC algorithm based on semantic classification is proposed. Firstly, the traditional algorithm is analyzed. Aiming at some problems existing in the traditional algorithm, a clustering algorithm model based on term meaning and collaborative filtering algorithm is designed by combining the collaborative filtering algorithm and project-based clustering algorithm. Before analyzing sparse data, the cold start and timeliness of the traditional algorithm are improved. Secondly, the performance comparison of three cosine similarity calculation methods of experimental IBCF algorithm, the performance comparison between CF-LFMC algorithm and IBCF algorithm, and the performance comparison between CF-LFMC algorithm and CF-LFMC algorithm without the time function is carried out. The clustering value N = 10 in the CF-LFMC algorithm is taken as the experimental result; MAE values of both algorithms decrease with the increase of the nearest neighbor number k. When the number of nearest neighbors is small, MAE values of the two algorithms are close to each other. As the number of nearest neighbors increases, the accuracy of the algorithm does not improve significantly, and the calculation cost of the algorithm will increase with the increase of the number of nearest neighbors, so the number of nearest neighbors between 20 and 30 is more appropriate. CF-LFMC shows better accuracy, and the CF-LFMC algorithm improved by the time function has improved the accuracy, which is better than the traditional algorithm in accuracy.
{"title":"Research and Implementation of Digital Media Recommendation System Based on Semantic Classification","authors":"Xiaoguang Li","doi":"10.1155/2022/4070827","DOIUrl":"https://doi.org/10.1155/2022/4070827","url":null,"abstract":"In order to study the recommendation system of digital media based on semantic classification, the CF-LFMC algorithm based on semantic classification is proposed. Firstly, the traditional algorithm is analyzed. Aiming at some problems existing in the traditional algorithm, a clustering algorithm model based on term meaning and collaborative filtering algorithm is designed by combining the collaborative filtering algorithm and project-based clustering algorithm. Before analyzing sparse data, the cold start and timeliness of the traditional algorithm are improved. Secondly, the performance comparison of three cosine similarity calculation methods of experimental IBCF algorithm, the performance comparison between CF-LFMC algorithm and IBCF algorithm, and the performance comparison between CF-LFMC algorithm and CF-LFMC algorithm without the time function is carried out. The clustering value N = 10 in the CF-LFMC algorithm is taken as the experimental result; MAE values of both algorithms decrease with the increase of the nearest neighbor number k. When the number of nearest neighbors is small, MAE values of the two algorithms are close to each other. As the number of nearest neighbors increases, the accuracy of the algorithm does not improve significantly, and the calculation cost of the algorithm will increase with the increase of the number of nearest neighbors, so the number of nearest neighbors between 20 and 30 is more appropriate. CF-LFMC shows better accuracy, and the CF-LFMC algorithm improved by the time function has improved the accuracy, which is better than the traditional algorithm in accuracy.","PeriodicalId":415473,"journal":{"name":"Adv. Multim.","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129074184","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：