Pub Date : 2021-11-01DOI: 10.1109/CONF-SPML54095.2021.00067
Luyu Zeng, Zhong Zheng, Rui Zhang
The outbreak of Covld-19 has put tremendous pressure on medical systems around the world. The highly infectious nature of this respiratory disease challenges advanced diagnostic technology to achieve rapid, scalable, affordable, and high-precision testing. In previous studies, Tsiknakis used Convolutional Neural Network (CNN) and transfer learning to achieved high accuracy in distinguishing the lung X-ray images of Covid-19 infectors and healthy people. However, its accuracy is not so high in quaternary classification (Bacterial Pneumonia, Covidl9, Normal, and Viral Pneumonia). It can hardly distinguish between bacterial pneumonia and viral pneumonia. Based on CNN, transfer learning, and interpretable machine learning methods, this work precisely implements data processing and augmentation and adds a second binary classifier following a confidence level. In this way, the accuracy and recall rate of the quaternary classification are significantly improved, especially for bacterial pneumonia and viral pneumonia, and the model also becomes more interpretable.
{"title":"Pneumonia X-ray Imaging Classification Based on an Interpretable Machine Learning Model","authors":"Luyu Zeng, Zhong Zheng, Rui Zhang","doi":"10.1109/CONF-SPML54095.2021.00067","DOIUrl":"https://doi.org/10.1109/CONF-SPML54095.2021.00067","url":null,"abstract":"The outbreak of Covld-19 has put tremendous pressure on medical systems around the world. The highly infectious nature of this respiratory disease challenges advanced diagnostic technology to achieve rapid, scalable, affordable, and high-precision testing. In previous studies, Tsiknakis used Convolutional Neural Network (CNN) and transfer learning to achieved high accuracy in distinguishing the lung X-ray images of Covid-19 infectors and healthy people. However, its accuracy is not so high in quaternary classification (Bacterial Pneumonia, Covidl9, Normal, and Viral Pneumonia). It can hardly distinguish between bacterial pneumonia and viral pneumonia. Based on CNN, transfer learning, and interpretable machine learning methods, this work precisely implements data processing and augmentation and adds a second binary classifier following a confidence level. In this way, the accuracy and recall rate of the quaternary classification are significantly improved, especially for bacterial pneumonia and viral pneumonia, and the model also becomes more interpretable.","PeriodicalId":415094,"journal":{"name":"2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126496752","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}
Pub Date : 2021-11-01DOI: 10.1109/CONF-SPML54095.2021.00027
Timing Yang, Chen Jiang, Qi Meng
In order to monitor the crystallization process of L-glutamic acid online, a real-time detection method based on non-invasive image analysis has been proposed to obtain in-situ images, and a deep-learning based network Mask R-CNN is applied to detect target crystals in images. Considering deep-learning network requires an enormous amount of dataset with labelled region of interest (RoI) samples, this paper proposes semi-automatic labelling methods to reduce human work when generating the dataset. By applying another Mask R-CNN for labelling the dataset, human work can be reduced from labelling the whole dataset to filtering the detection results of the labeller Mask R-CNN. The final detection results prove the feasibility of this method. The proposed method is also proved to be more feasible and reliable than transfer learning.
{"title":"Optimized Methods for Online Monitoring of L-Glutamic Acid Crystallization","authors":"Timing Yang, Chen Jiang, Qi Meng","doi":"10.1109/CONF-SPML54095.2021.00027","DOIUrl":"https://doi.org/10.1109/CONF-SPML54095.2021.00027","url":null,"abstract":"In order to monitor the crystallization process of L-glutamic acid online, a real-time detection method based on non-invasive image analysis has been proposed to obtain in-situ images, and a deep-learning based network Mask R-CNN is applied to detect target crystals in images. Considering deep-learning network requires an enormous amount of dataset with labelled region of interest (RoI) samples, this paper proposes semi-automatic labelling methods to reduce human work when generating the dataset. By applying another Mask R-CNN for labelling the dataset, human work can be reduced from labelling the whole dataset to filtering the detection results of the labeller Mask R-CNN. The final detection results prove the feasibility of this method. The proposed method is also proved to be more feasible and reliable than transfer learning.","PeriodicalId":415094,"journal":{"name":"2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122761439","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}
Pub Date : 2021-11-01DOI: 10.1109/CONF-SPML54095.2021.00019
Hao Li
With the growing demand for better performance of remote sensing (RS) image classification, a variety of methods have been proposed in RS image classification field in recent years. In general, there are two categories of RS image classification methods: pixel-based (PB) approach and object-based (OB) approach. In this paper, RS image classification methods are reviewed from the perspective of PB approach and OB approach and, specifically, the development and characteristics of a promising methodology for RS image classification named support vector machine (SVM) are surveyed. SVM is particularly popular in the RS field since it can deal with small-sized training dataset and provide higher classification accuracy than some traditional methods like maximum likelihood classifier. Besides, SVM has advantages of high memory-efficiency and strong generalization. However, SVM-based approaches also suffer from some problems. For instance, SVM-based methods tend to overfit due to inappropriate choice of kernel functions and it is inefficient for them to determine the optimum kernel function parameters as well as to process hyperspectral images. This paper also proposes the improvement of SVM-based methods aiming to address the limitations and improve the performance of SVM in RS image classification field. Moreover, future directions for SVM in RS image classification field are presented, expecting to help researchers to find possible research focuses in the future.
{"title":"An Overview on Remote Sensing Image Classification Methods with a Focus on Support Vector Machine","authors":"Hao Li","doi":"10.1109/CONF-SPML54095.2021.00019","DOIUrl":"https://doi.org/10.1109/CONF-SPML54095.2021.00019","url":null,"abstract":"With the growing demand for better performance of remote sensing (RS) image classification, a variety of methods have been proposed in RS image classification field in recent years. In general, there are two categories of RS image classification methods: pixel-based (PB) approach and object-based (OB) approach. In this paper, RS image classification methods are reviewed from the perspective of PB approach and OB approach and, specifically, the development and characteristics of a promising methodology for RS image classification named support vector machine (SVM) are surveyed. SVM is particularly popular in the RS field since it can deal with small-sized training dataset and provide higher classification accuracy than some traditional methods like maximum likelihood classifier. Besides, SVM has advantages of high memory-efficiency and strong generalization. However, SVM-based approaches also suffer from some problems. For instance, SVM-based methods tend to overfit due to inappropriate choice of kernel functions and it is inefficient for them to determine the optimum kernel function parameters as well as to process hyperspectral images. This paper also proposes the improvement of SVM-based methods aiming to address the limitations and improve the performance of SVM in RS image classification field. Moreover, future directions for SVM in RS image classification field are presented, expecting to help researchers to find possible research focuses in the future.","PeriodicalId":415094,"journal":{"name":"2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127730353","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}
Pub Date : 2021-11-01DOI: 10.1109/CONF-SPML54095.2021.00056
Si-Hao Du, Yi. Gu, Yuewei Zhu
Zillow’s is a real estate company that relies on the estimated costs of a house to set its price. The log error of prediction is calculated by the log difference between the prediction and the actual sale price. Thusly, the goal of this work is trying to minimize this error in order to improve accuracy. Due to the fact that real estate dataset has multiple feature blanks, preprocessing methods of the data show large significance in this work. On the other hand, particularly important features are selected, and several machine learning models— Decision Tree, Random Forest, Linear Regression— are applied to predict. In conclusion, Linear Regression performs better than the other two models. Some future work, like feature engineering methods, can be done to further improve the accuracy.
{"title":"Big Data Classification and Machine Learning Using Zillow Estimates","authors":"Si-Hao Du, Yi. Gu, Yuewei Zhu","doi":"10.1109/CONF-SPML54095.2021.00056","DOIUrl":"https://doi.org/10.1109/CONF-SPML54095.2021.00056","url":null,"abstract":"Zillow’s is a real estate company that relies on the estimated costs of a house to set its price. The log error of prediction is calculated by the log difference between the prediction and the actual sale price. Thusly, the goal of this work is trying to minimize this error in order to improve accuracy. Due to the fact that real estate dataset has multiple feature blanks, preprocessing methods of the data show large significance in this work. On the other hand, particularly important features are selected, and several machine learning models— Decision Tree, Random Forest, Linear Regression— are applied to predict. In conclusion, Linear Regression performs better than the other two models. Some future work, like feature engineering methods, can be done to further improve the accuracy.","PeriodicalId":415094,"journal":{"name":"2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132798521","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}
Pub Date : 2021-11-01DOI: 10.1109/CONF-SPML54095.2021.00057
Linze Shi, Yuting Zhou
Traffic sign detection and classification is one of the main tasks of the advanced driving assistance system (ADAS). It is an integral part of the automatic driving vehicle. How to improve the accuracy and detection speed of traffic sign recognition has always been the focus of research. To solve the above problems, a fast three-stage traffic sign detection and classification method is proposed in this paper to improve the algorithm accuracy. In the first stage, we develop a probability distribution model based on the color, location, and type of traffic signs as a priori information, which can drastically minimize the search range of signs and enhance detection efficiency. In the second stage, this paper proposes an image color segmentation method based on Gaussian mixture model (GMM) as the detection module, uses the YCbCr color model for image segmentation. The morphological closure is then performed to refine the segmented image. In the third stage, the classification module classifies the extracted target areas through deep convolutional neural network (CNN).
{"title":"A CNN-based Traffic Sign Detection and Classification Method Using Priori Knowledge","authors":"Linze Shi, Yuting Zhou","doi":"10.1109/CONF-SPML54095.2021.00057","DOIUrl":"https://doi.org/10.1109/CONF-SPML54095.2021.00057","url":null,"abstract":"Traffic sign detection and classification is one of the main tasks of the advanced driving assistance system (ADAS). It is an integral part of the automatic driving vehicle. How to improve the accuracy and detection speed of traffic sign recognition has always been the focus of research. To solve the above problems, a fast three-stage traffic sign detection and classification method is proposed in this paper to improve the algorithm accuracy. In the first stage, we develop a probability distribution model based on the color, location, and type of traffic signs as a priori information, which can drastically minimize the search range of signs and enhance detection efficiency. In the second stage, this paper proposes an image color segmentation method based on Gaussian mixture model (GMM) as the detection module, uses the YCbCr color model for image segmentation. The morphological closure is then performed to refine the segmented image. In the third stage, the classification module classifies the extracted target areas through deep convolutional neural network (CNN).","PeriodicalId":415094,"journal":{"name":"2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133647463","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}
Pub Date : 2021-11-01DOI: 10.1109/CONF-SPML54095.2021.00051
Chixun Zhang
In recent years, high-resolution optical microscopy has developed rapidly and its resolution has been increasing, and the point spread function directly affects the resolution. In this paper I generate a point spread function for an aperture-based imaging system (a lens with a shaped aperture). I also generate a flat-top signal (uniformly illuminated circular unobstructed aperture) and a pupil-masked two-dimensional Fourier transform and pass through an inverse oscillation filter, and compare them by analyzing the centrality of the spectrum, frequency distribution, and energy distribution.
{"title":"A Method for Generating PSF Based on 2-D Fast Fourier Transform","authors":"Chixun Zhang","doi":"10.1109/CONF-SPML54095.2021.00051","DOIUrl":"https://doi.org/10.1109/CONF-SPML54095.2021.00051","url":null,"abstract":"In recent years, high-resolution optical microscopy has developed rapidly and its resolution has been increasing, and the point spread function directly affects the resolution. In this paper I generate a point spread function for an aperture-based imaging system (a lens with a shaped aperture). I also generate a flat-top signal (uniformly illuminated circular unobstructed aperture) and a pupil-masked two-dimensional Fourier transform and pass through an inverse oscillation filter, and compare them by analyzing the centrality of the spectrum, frequency distribution, and energy distribution.","PeriodicalId":415094,"journal":{"name":"2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)","volume":"30 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124817137","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}
Pub Date : 2021-11-01DOI: 10.1109/CONF-SPML54095.2021.00014
Bangqi Guo, Chujiao Peng
The system studied in this study is specifically used for the measurement of the optical transmittance of liquid crystal filters. In practical applications, liquid crystal filters are mainly used in the production of welding masks. Therefore, the optical transmittance of the liquid crystal filter is an important parameter of the entire liquid crystal material, which is of great significance to the performance of the welding mask products. This study is aimed at the optical transmittance measurement system with white light as the light source. The system include s a light source, an integrating sphere, and a luxmeter. The core point of this system is that the photodetector detects the electrical signal at the opening on the side of the integrating sphere and compares it with the standard illuminance meter. The light intensity measured at the front opening is subjected to a fitting calibration, so that the detected optical signal measured at the opening on the side of the integrating sphere represents the light intensity at the front opening of the integrating sphere. The equipment needs to be measured in a dark room. The test results prove that the low collimation of the light source has a certain impact on the experimental results. The test results show that after debugging, the light signal detected at the opening on the side of the integrating sphere can accurately represent the light intensity measured by the standard illuminance meter at the front opening.
{"title":"Design of Photoelectric Signal Parameter Test System for Liquid Crystal Filters","authors":"Bangqi Guo, Chujiao Peng","doi":"10.1109/CONF-SPML54095.2021.00014","DOIUrl":"https://doi.org/10.1109/CONF-SPML54095.2021.00014","url":null,"abstract":"The system studied in this study is specifically used for the measurement of the optical transmittance of liquid crystal filters. In practical applications, liquid crystal filters are mainly used in the production of welding masks. Therefore, the optical transmittance of the liquid crystal filter is an important parameter of the entire liquid crystal material, which is of great significance to the performance of the welding mask products. This study is aimed at the optical transmittance measurement system with white light as the light source. The system include s a light source, an integrating sphere, and a luxmeter. The core point of this system is that the photodetector detects the electrical signal at the opening on the side of the integrating sphere and compares it with the standard illuminance meter. The light intensity measured at the front opening is subjected to a fitting calibration, so that the detected optical signal measured at the opening on the side of the integrating sphere represents the light intensity at the front opening of the integrating sphere. The equipment needs to be measured in a dark room. The test results prove that the low collimation of the light source has a certain impact on the experimental results. The test results show that after debugging, the light signal detected at the opening on the side of the integrating sphere can accurately represent the light intensity measured by the standard illuminance meter at the front opening.","PeriodicalId":415094,"journal":{"name":"2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)","volume":" 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132187724","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}
Pub Date : 2021-11-01DOI: 10.1109/CONF-SPML54095.2021.00055
Yuyang Wang
Every year, the negligence of drivers leads to many accidents. According to World Health Organization, approximately 1.3 million people die each year due to road traffic crashes. Safety is the main factor driving the growth of demand for autonomous vehicles. When vehicles go on the road, decision-making plays a crucial role in the autonomous driving system. This paper proposes an approach based on the value-iteration for Markov Decision Process to train the autonomous car to drive appropriately on the single-track road. By following the optimal policy from value-iteration, the simulation on CARLO shows the results of decision-making for autonomous vehicles under a single-track road scenario. This work makes a contribution on decision-making for cars at single-lane road.
{"title":"Decision Making for Autonomous Vehicle at Single-Lane Road Under Uncertainties","authors":"Yuyang Wang","doi":"10.1109/CONF-SPML54095.2021.00055","DOIUrl":"https://doi.org/10.1109/CONF-SPML54095.2021.00055","url":null,"abstract":"Every year, the negligence of drivers leads to many accidents. According to World Health Organization, approximately 1.3 million people die each year due to road traffic crashes. Safety is the main factor driving the growth of demand for autonomous vehicles. When vehicles go on the road, decision-making plays a crucial role in the autonomous driving system. This paper proposes an approach based on the value-iteration for Markov Decision Process to train the autonomous car to drive appropriately on the single-track road. By following the optimal policy from value-iteration, the simulation on CARLO shows the results of decision-making for autonomous vehicles under a single-track road scenario. This work makes a contribution on decision-making for cars at single-lane road.","PeriodicalId":415094,"journal":{"name":"2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117296060","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}
Pub Date : 2021-11-01DOI: 10.1109/CONF-SPML54095.2021.00063
Yuting Zhou, Linze Shi, Bo Yuan
With the development of deep learning, image recognition technology has made great progress. However, there is often occlusion in the image recognition task. Object occlusion not only loses part of the target information, but also introduces additional interference, thus exacerbating the difficulty of image recognition. This paper aims to improve the recognition rate of fruits and vegetables in the presence of occlusion, so as to alert people to the timely disposal of food in the refrigerator when it is nearing its expiration date. To this end, this paper employs the Alexnet architecture and revises it for better feature extraction, and combines it with a generative adversarial network (GAN), which trains a generator and a discriminator with pairs of occluded and non-occluded images, and finally recover the occluded images. Experimental results show that the proposed system improves the accuracy of fruit and vegetable recognition, and can be better used in smart refrigerators to remind the shelf life of fruits and vegetables.
{"title":"A Generative Adversarial Network-based Framework for Fruit and Vegetable Occlusion Detection in Smart Refrigerators","authors":"Yuting Zhou, Linze Shi, Bo Yuan","doi":"10.1109/CONF-SPML54095.2021.00063","DOIUrl":"https://doi.org/10.1109/CONF-SPML54095.2021.00063","url":null,"abstract":"With the development of deep learning, image recognition technology has made great progress. However, there is often occlusion in the image recognition task. Object occlusion not only loses part of the target information, but also introduces additional interference, thus exacerbating the difficulty of image recognition. This paper aims to improve the recognition rate of fruits and vegetables in the presence of occlusion, so as to alert people to the timely disposal of food in the refrigerator when it is nearing its expiration date. To this end, this paper employs the Alexnet architecture and revises it for better feature extraction, and combines it with a generative adversarial network (GAN), which trains a generator and a discriminator with pairs of occluded and non-occluded images, and finally recover the occluded images. Experimental results show that the proposed system improves the accuracy of fruit and vegetable recognition, and can be better used in smart refrigerators to remind the shelf life of fruits and vegetables.","PeriodicalId":415094,"journal":{"name":"2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116403893","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}
Pub Date : 2021-11-01DOI: 10.1109/CONF-SPML54095.2021.00061
Hui-Chu Shu
As one of the most popular probabilistic programming tools, PyMC3 can solve inference problems in many scientific fields. In this paper, we used PyMC3 to build a Bayesian model for the census-house dataset to predict the correspondence between the U.S. population and house prices, and evaluated it using the dataset to determine the validity and accuracy of the established model. Through the evaluation of this dataset, the Bayesian model established in this paper can predict the theoretical data of house prices with high accuracy in the absence of COVID-19, which has implications for the study of the current property prices that have increased significantly because of COVID-19 and the due prices of similar large assets, researchers can predict the house prices in the absence of COVID-19, and then based on the current house prices calculate the difference and thus study the impact of COVID-19 in terms of house prices as well as the impact of similar asset prices.
{"title":"Bayesian Inference in Census-House Dataset","authors":"Hui-Chu Shu","doi":"10.1109/CONF-SPML54095.2021.00061","DOIUrl":"https://doi.org/10.1109/CONF-SPML54095.2021.00061","url":null,"abstract":"As one of the most popular probabilistic programming tools, PyMC3 can solve inference problems in many scientific fields. In this paper, we used PyMC3 to build a Bayesian model for the census-house dataset to predict the correspondence between the U.S. population and house prices, and evaluated it using the dataset to determine the validity and accuracy of the established model. Through the evaluation of this dataset, the Bayesian model established in this paper can predict the theoretical data of house prices with high accuracy in the absence of COVID-19, which has implications for the study of the current property prices that have increased significantly because of COVID-19 and the due prices of similar large assets, researchers can predict the house prices in the absence of COVID-19, and then based on the current house prices calculate the difference and thus study the impact of COVID-19 in terms of house prices as well as the impact of similar asset prices.","PeriodicalId":415094,"journal":{"name":"2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116345120","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：