We propose a face image restoration method that combines feature fusion and attention mechanisms for the current image restoration field that generates blurred images, artifacts, inconsistent texture and structure fusion. The model divides image restoration into two stages. First, the edge information repaired by the edge generation adversarial network is used as the prior knowledge of the image, and then the generated prior knowledge and the broken image are put into the image repair network to generate the complete image. We introduce a texture-structure feature fusion method in the generator structure to solve the texture and structure fusion inconsistency problem and use a dense residual layer-hopping connection to mitigate the gradient disappearance problem while speeding up the model convergence and introduce a spatial and channel attention mechanism to generate correct semantic connections to enhance the model performance and suppress image blurring. We apply the algorithm to the CelebA-HQ face dataset, and compared with the current mainstream restoration algorithms, quantitative analysis shows that the method in this paper outperforms in three metrics, PSNR, SSIM, and L1.
{"title":"Combining feature fusion and attention mechanism for face image restoration","authors":"Jiangtao Liu, Yan Wei, Jinzhi Deng","doi":"10.1117/12.2671240","DOIUrl":"https://doi.org/10.1117/12.2671240","url":null,"abstract":"We propose a face image restoration method that combines feature fusion and attention mechanisms for the current image restoration field that generates blurred images, artifacts, inconsistent texture and structure fusion. The model divides image restoration into two stages. First, the edge information repaired by the edge generation adversarial network is used as the prior knowledge of the image, and then the generated prior knowledge and the broken image are put into the image repair network to generate the complete image. We introduce a texture-structure feature fusion method in the generator structure to solve the texture and structure fusion inconsistency problem and use a dense residual layer-hopping connection to mitigate the gradient disappearance problem while speeding up the model convergence and introduce a spatial and channel attention mechanism to generate correct semantic connections to enhance the model performance and suppress image blurring. We apply the algorithm to the CelebA-HQ face dataset, and compared with the current mainstream restoration algorithms, quantitative analysis shows that the method in this paper outperforms in three metrics, PSNR, SSIM, and L1.","PeriodicalId":227528,"journal":{"name":"International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128295402","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}
Single image super-resolution is an approach to optimize the image stripe structure and improve the image quality. Recently, it developed rapidly based on convolution neural network, specially designed for this task, which becomes a hot topic of research and have shown remarkable result. Recently, many models have been developed based on Generative Adversarial Networks (GAN) and display enormous superiority compared with traditional deep learning methods. In GANs settings, adversarial loss pushes the generated image to natural image manifold with the help of a discriminator and at the same time trains discriminator to better discriminate the real image from those fake images generated by generator. In this course of confrontation, the generator is excellently trained and have achieved outstanding performance in the image super-resolution task. However, the traditional SRGAN image super-resolution reconstruction algorithm has slow training convergence speed. Moreover, excessive high-frequency texture sharpening leads to distortion of some details, which has a negative impact on the reconstructed image. In this work, curriculum learning algorithm is implemented to solve these problems and thus originally propose CL-SRGAN method, which is designed to help SRGAN achieve better performance on image resolution task. In the final experiment, CL-SRGAN has made an effective breakthrough in processing image reconstruction.
{"title":"CL-SRGAN: generative adversary network equipped with curriculum learning for image super-resolution","authors":"Mei-Shuo Chen, Kang Li, Zhexu Luo, Chengxuan Zou","doi":"10.1117/12.2671421","DOIUrl":"https://doi.org/10.1117/12.2671421","url":null,"abstract":"Single image super-resolution is an approach to optimize the image stripe structure and improve the image quality. Recently, it developed rapidly based on convolution neural network, specially designed for this task, which becomes a hot topic of research and have shown remarkable result. Recently, many models have been developed based on Generative Adversarial Networks (GAN) and display enormous superiority compared with traditional deep learning methods. In GANs settings, adversarial loss pushes the generated image to natural image manifold with the help of a discriminator and at the same time trains discriminator to better discriminate the real image from those fake images generated by generator. In this course of confrontation, the generator is excellently trained and have achieved outstanding performance in the image super-resolution task. However, the traditional SRGAN image super-resolution reconstruction algorithm has slow training convergence speed. Moreover, excessive high-frequency texture sharpening leads to distortion of some details, which has a negative impact on the reconstructed image. In this work, curriculum learning algorithm is implemented to solve these problems and thus originally propose CL-SRGAN method, which is designed to help SRGAN achieve better performance on image resolution task. In the final experiment, CL-SRGAN has made an effective breakthrough in processing image reconstruction.","PeriodicalId":227528,"journal":{"name":"International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128632968","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}
Taking aerobics as an example, the human movement can be regarded as a series of posture data that changes over time. Compared with other methods, the special kinematic feature model of human skeleton has great advantages in describing the posture change state. In order to achieve the accurate capture of dynamic posture of aerobics, so as to complete the recognition and analysis of motion posture data in a short time, this paper proposes a 3D human dynamic posture recognition method based on Long Short-Term Memory (LSTM) network. First, the first frame model of the 3D human action sequence is selected as the template of the sequence, and the shape difference of the subsequent models of the action sequence is calculated by the shape difference operator relative to the template, which is represented as a low-dimensional shape difference information tensor. Then, the spatial and temporal dimensional features are extracted from the shape difference information tensor by combining two-dimensional convolutional neural network and LSTM to achieve the recognition of human dynamic posture. The above methods were evaluated by the dynamic pose datasets HumanEva, MoSh, SFU, SSM and Transitions; The classification accuracies were 98.4%, 99.7%, 100%, 99.4% and 100%, respectively.
{"title":"Research on aerobics action pose recognition based on deep learning","authors":"Baoping Xing, Huan Li, Nathan Chen","doi":"10.1117/12.2671200","DOIUrl":"https://doi.org/10.1117/12.2671200","url":null,"abstract":"Taking aerobics as an example, the human movement can be regarded as a series of posture data that changes over time. Compared with other methods, the special kinematic feature model of human skeleton has great advantages in describing the posture change state. In order to achieve the accurate capture of dynamic posture of aerobics, so as to complete the recognition and analysis of motion posture data in a short time, this paper proposes a 3D human dynamic posture recognition method based on Long Short-Term Memory (LSTM) network. First, the first frame model of the 3D human action sequence is selected as the template of the sequence, and the shape difference of the subsequent models of the action sequence is calculated by the shape difference operator relative to the template, which is represented as a low-dimensional shape difference information tensor. Then, the spatial and temporal dimensional features are extracted from the shape difference information tensor by combining two-dimensional convolutional neural network and LSTM to achieve the recognition of human dynamic posture. The above methods were evaluated by the dynamic pose datasets HumanEva, MoSh, SFU, SSM and Transitions; The classification accuracies were 98.4%, 99.7%, 100%, 99.4% and 100%, respectively.","PeriodicalId":227528,"journal":{"name":"International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129562371","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 Chinese medical question and answer task, question intention detection is a very important part. At present, the common intention detection methods mainly use the manually designed matching rules to find the problem features to detect the intention of the problem, but the use of a large amount of labor usually brings about problems such as high cost and poor versatility. A novel method of intention detection is proposed in this paper. First, the collected questions with different intention categories are used to construct intention feature words. Then, based on the BERT pre-training language model, a two-classification model of phrase similarity is constructed. By comparing the combination results of problem word segmentation and the similarity of intention feature words, the multi-classification problem of problem intention detection is transformed into a two-classification problem between multiple phrases. Then we can get the inclination of the question for each intention category, that is the intention category of the question. The experiment shows that the method based on the two-classification model of phrase similarity has better effect than the previous methods, and the F1 value in the test set reaches 90.1.
{"title":"Research on intention tendency detection for Chinese medical question answering task","authors":"Musheng Chen, Ying Liu, Junhua Wu","doi":"10.1117/12.2671431","DOIUrl":"https://doi.org/10.1117/12.2671431","url":null,"abstract":"In the Chinese medical question and answer task, question intention detection is a very important part. At present, the common intention detection methods mainly use the manually designed matching rules to find the problem features to detect the intention of the problem, but the use of a large amount of labor usually brings about problems such as high cost and poor versatility. A novel method of intention detection is proposed in this paper. First, the collected questions with different intention categories are used to construct intention feature words. Then, based on the BERT pre-training language model, a two-classification model of phrase similarity is constructed. By comparing the combination results of problem word segmentation and the similarity of intention feature words, the multi-classification problem of problem intention detection is transformed into a two-classification problem between multiple phrases. Then we can get the inclination of the question for each intention category, that is the intention category of the question. The experiment shows that the method based on the two-classification model of phrase similarity has better effect than the previous methods, and the F1 value in the test set reaches 90.1.","PeriodicalId":227528,"journal":{"name":"International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128917414","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}
Due to the complex spatio-temporal correlation of meteorological data, weather forecasting is a challenging task. Recently, with plenty of meteorological data available and the successful applications of deep learning technology in many areas, developing data-driven models for this task has achieved great attention. Especially, Convolutional Recurrent Neural Networks (CRNNs) have been shown to be effective in spatio-temporal predictive learning. The convolutional connection with shared weights is fixed for different spatial locations and timestamps, while spatio-temporal transformations of meteorological data are varying in both time and space. To address this problem, we developed a Spatio-Temporal Adaptive Convolution for the Gated Recurrent Unit (GRU) to improve the ability of extracting spatio-temporal features. For convenience, we abbreviate our model as STAConvGRU for weather forecasting. The key motivation behind STAConvGRU is to develop additional convolution layers under the framework of the ordinary RNN to learn simultaneously the sampling positions and weights of convolutional kernels. As a result, the adaptive convolution could select the positions and adjust the weights according to the spatio-temporal information. Comparative experiments are conducted on four types of meteorological datasets, including temperature, relative humidity, wind, and radar echo. The experimental results demonstrate the effectiveness and superiority of our proposed model.
{"title":"STACnovGRU: weather forecasting based on spatio-temporal adaptive convolutional GRU","authors":"Deping Xiang, Pu Zhang, Shiming Xiang","doi":"10.1117/12.2671060","DOIUrl":"https://doi.org/10.1117/12.2671060","url":null,"abstract":"Due to the complex spatio-temporal correlation of meteorological data, weather forecasting is a challenging task. Recently, with plenty of meteorological data available and the successful applications of deep learning technology in many areas, developing data-driven models for this task has achieved great attention. Especially, Convolutional Recurrent Neural Networks (CRNNs) have been shown to be effective in spatio-temporal predictive learning. The convolutional connection with shared weights is fixed for different spatial locations and timestamps, while spatio-temporal transformations of meteorological data are varying in both time and space. To address this problem, we developed a Spatio-Temporal Adaptive Convolution for the Gated Recurrent Unit (GRU) to improve the ability of extracting spatio-temporal features. For convenience, we abbreviate our model as STAConvGRU for weather forecasting. The key motivation behind STAConvGRU is to develop additional convolution layers under the framework of the ordinary RNN to learn simultaneously the sampling positions and weights of convolutional kernels. As a result, the adaptive convolution could select the positions and adjust the weights according to the spatio-temporal information. Comparative experiments are conducted on four types of meteorological datasets, including temperature, relative humidity, wind, and radar echo. The experimental results demonstrate the effectiveness and superiority of our proposed model.","PeriodicalId":227528,"journal":{"name":"International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132143029","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}
Lixue Tian, Xianjie Huo, Zhishuai Zhang, Wenzhe Ma, Yingtao Li
In this paper, low dropout voltage regulator based on Flipped Voltage Follower (FVF) is proposed. It is futured with fast transient response to load changes, high slew rate, and faster power-on time. The circuit proposed in the paper is adopted with double error amplifier and transient enhancement circuit. The major error amplifier can provide reference voltage for FVF structure and ensure flipped voltage stability. The auxiliary error amplifier is used to form a feedback loop at VOUT and VREF, improving the precision of output voltage, generating extra charge and discharge branch to provide greater slew rate, faster loop response, and faster power-on speed. The simulation results show that this LDO has output voltage jump less than 33mV and 150ns power-on time.
{"title":"Low dropout regulator with double operational amplifiers based on FVF structure","authors":"Lixue Tian, Xianjie Huo, Zhishuai Zhang, Wenzhe Ma, Yingtao Li","doi":"10.1117/12.2671149","DOIUrl":"https://doi.org/10.1117/12.2671149","url":null,"abstract":"In this paper, low dropout voltage regulator based on Flipped Voltage Follower (FVF) is proposed. It is futured with fast transient response to load changes, high slew rate, and faster power-on time. The circuit proposed in the paper is adopted with double error amplifier and transient enhancement circuit. The major error amplifier can provide reference voltage for FVF structure and ensure flipped voltage stability. The auxiliary error amplifier is used to form a feedback loop at VOUT and VREF, improving the precision of output voltage, generating extra charge and discharge branch to provide greater slew rate, faster loop response, and faster power-on speed. The simulation results show that this LDO has output voltage jump less than 33mV and 150ns power-on time.","PeriodicalId":227528,"journal":{"name":"International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129232772","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}
Liquid level monitoring is widely used in industrial systems monitoring. Accurate monitoring of liquid levels is an essential tool in the production control process, especially for monitoring the status of oil storage tanks. In order to improve the accuracy of the storage tank monitoring system, this paper designs an intelligent monitoring system based on infrared thermal imaging for storage tank level monitoring. The hardware part of the level measurement system is mainly composed of the host computer, microcontroller, head, and infrared thermal imager. The software design consists of the following aspects: level image acquisition based on infrared thermal imaging, level measurement using ultrasonic characteristics, and level monitoring using input transmitters. By comparing this system with a conventional monitoring system, the experimental results were obtained: the relative error of the monitoring system in this paper was 0.8%. The relative error range of the conventional system is 2.6% to 5.8%. It can be seen that the system in this paper is better than the traditional system, and the experiment is successful. The oil storage tank level monitoring system designed in this paper has the advantages of accurate monitoring, stable operation, simple operation, and simple implementation of network management, and it has broad application prospects.
{"title":"Intelligent monitoring system of oil tank liquid level based on infrared thermal imaging","authors":"Feng Liu, Yingbo Li","doi":"10.1117/12.2672730","DOIUrl":"https://doi.org/10.1117/12.2672730","url":null,"abstract":"Liquid level monitoring is widely used in industrial systems monitoring. Accurate monitoring of liquid levels is an essential tool in the production control process, especially for monitoring the status of oil storage tanks. In order to improve the accuracy of the storage tank monitoring system, this paper designs an intelligent monitoring system based on infrared thermal imaging for storage tank level monitoring. The hardware part of the level measurement system is mainly composed of the host computer, microcontroller, head, and infrared thermal imager. The software design consists of the following aspects: level image acquisition based on infrared thermal imaging, level measurement using ultrasonic characteristics, and level monitoring using input transmitters. By comparing this system with a conventional monitoring system, the experimental results were obtained: the relative error of the monitoring system in this paper was 0.8%. The relative error range of the conventional system is 2.6% to 5.8%. It can be seen that the system in this paper is better than the traditional system, and the experiment is successful. The oil storage tank level monitoring system designed in this paper has the advantages of accurate monitoring, stable operation, simple operation, and simple implementation of network management, and it has broad application prospects.","PeriodicalId":227528,"journal":{"name":"International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022)","volume":"59 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114088123","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 science and technology and the advent of the information age, the number of components used in electronic devices has increased sharply, making its internal circuit structure increasingly complex. Printed Circuit Boards (PCBs), as part of electronic devices, are becoming smaller and more integrated, resulting in a much greater increase in the probability of failure and the difficulty of detection. Therefore, to reduce the difficulty and cost of PCB fault diagnosis, it is very necessary to explore and study new PCB diagnosis methods. This paper first reconstructs the PCB dataset by ESRGAN, and then the CenterNet based on the center point is introduced and improved. The ResNeSt based on the segmentation attention mechanism is integrated with CenterNet to realize the PCBs fault diagnosis method based on the tiny object detection method. Experiments have proved that the method can achieve 99.42% mAP.
{"title":"A novel PCB fault diagnosis method based on tiny object detection","authors":"Chengwei Kang, Peicheng Cong, Yongbo Sun, Shengqi Wang, Xi Liu, Longjie Duan, Kuan Wu, Peng Cao, Dong Qin, Changxiang Li, Xudong Song","doi":"10.1117/12.2671108","DOIUrl":"https://doi.org/10.1117/12.2671108","url":null,"abstract":"With the rapid development of science and technology and the advent of the information age, the number of components used in electronic devices has increased sharply, making its internal circuit structure increasingly complex. Printed Circuit Boards (PCBs), as part of electronic devices, are becoming smaller and more integrated, resulting in a much greater increase in the probability of failure and the difficulty of detection. Therefore, to reduce the difficulty and cost of PCB fault diagnosis, it is very necessary to explore and study new PCB diagnosis methods. This paper first reconstructs the PCB dataset by ESRGAN, and then the CenterNet based on the center point is introduced and improved. The ResNeSt based on the segmentation attention mechanism is integrated with CenterNet to realize the PCBs fault diagnosis method based on the tiny object detection method. Experiments have proved that the method can achieve 99.42% mAP.","PeriodicalId":227528,"journal":{"name":"International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115960943","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 solve the problem that the traditional feature matching algorithm has less premise number of feature points and poor matching ability under outdoor complex lighting conditions, an image matching algorithm based on color invariants in outdoor environment is proposed. Firstly, a feature matching algorithm with color invariants and Tanimoto similarity is designed based on Kubelka Munk theory. By introducing color invariants to distinguish the available feature areas in outdoor scenes, AKAZE (Accelerated KAZE) algorithm and SIFT (Scale invariant Feature Transform) algorithm are combined to generate more comprehensive feature descriptors; Then, Tanimoto similarity test is used to screen feature point pairs and random sample consensus algorithm is used to remove external points. According to the experimental results, under the same conditions, the improved algorithm obtains more effective feature points at the edge of the image and in the smooth area of the image. The average accuracy of the algorithm in outdoor environments reaches 90%, and the number of feature matching is 43% higher than that without color invariants.
{"title":"Image matching algorithm in outdoor environment","authors":"Ziyan Luo, Jian Qin, Long Yan","doi":"10.1117/12.2671319","DOIUrl":"https://doi.org/10.1117/12.2671319","url":null,"abstract":"In order to solve the problem that the traditional feature matching algorithm has less premise number of feature points and poor matching ability under outdoor complex lighting conditions, an image matching algorithm based on color invariants in outdoor environment is proposed. Firstly, a feature matching algorithm with color invariants and Tanimoto similarity is designed based on Kubelka Munk theory. By introducing color invariants to distinguish the available feature areas in outdoor scenes, AKAZE (Accelerated KAZE) algorithm and SIFT (Scale invariant Feature Transform) algorithm are combined to generate more comprehensive feature descriptors; Then, Tanimoto similarity test is used to screen feature point pairs and random sample consensus algorithm is used to remove external points. According to the experimental results, under the same conditions, the improved algorithm obtains more effective feature points at the edge of the image and in the smooth area of the image. The average accuracy of the algorithm in outdoor environments reaches 90%, and the number of feature matching is 43% higher than that without color invariants.","PeriodicalId":227528,"journal":{"name":"International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121030594","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 development of the Internet, more and more service-oriented industries are transforming from stores to build platforms on the internet, and so is the second-hand car sales industry, which not only saves the cost of opening stores and employees, but also facilitates the majority of car enthusiasts. But changing the transaction model to O2O is even more technical and professional car issues transferred to the owners and buyers. Consider that some sellers or buyers will have inadequate preparation and thus suffer from the transaction. Therefore, the platform needs to give estimated prices based on previous normal transaction data and after confirming the owner's real submission of used car information, so that the owner can adjust between prices, thus ensuring the quality and speed of the transaction. In this paper, we used desensitized data on second-hand car transactions provided by WUBA. After data cleaning, the main model was constructed by neural network, and the model was trained with the processed data. After validating the model, the factors that affected the transaction cycle were found out and optimized the model.
{"title":"Research on transaction optimization strategy based on data analysis of second-hand car trading platform","authors":"Yixuan An, Yuxin Zhao","doi":"10.1117/12.2671063","DOIUrl":"https://doi.org/10.1117/12.2671063","url":null,"abstract":"With the development of the Internet, more and more service-oriented industries are transforming from stores to build platforms on the internet, and so is the second-hand car sales industry, which not only saves the cost of opening stores and employees, but also facilitates the majority of car enthusiasts. But changing the transaction model to O2O is even more technical and professional car issues transferred to the owners and buyers. Consider that some sellers or buyers will have inadequate preparation and thus suffer from the transaction. Therefore, the platform needs to give estimated prices based on previous normal transaction data and after confirming the owner's real submission of used car information, so that the owner can adjust between prices, thus ensuring the quality and speed of the transaction. In this paper, we used desensitized data on second-hand car transactions provided by WUBA. After data cleaning, the main model was constructed by neural network, and the model was trained with the processed data. After validating the model, the factors that affected the transaction cycle were found out and optimized the model.","PeriodicalId":227528,"journal":{"name":"International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121228902","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：