Pub Date : 2019-10-01DOI: 10.1109/ISPCE-CN48734.2019.8958633
Jizhong Zhang, S. Lang, Qiang Wu, Chuan Liu
This study presents a method for material recognition using a pulsed time-of-flight (ToF) camera. The method measures the material bidirectional reflectance distribution function (BRDF) as a feature for material recognition by a pulsed ToF camera. We use the measurements of incident light at different angles to form the BRDF feature vectors. The feature vectors are used to build a training and test set to train and validate a classifier to perform the recognition. We choose the radial basis function (RBF) neural network as a classifier based on the nonlinear characteristics of material BRDF. Finally, we construct a turntable-based measurement system and use the material BRDF as the feature for classifying a variety of materials including metals and plastics. The optimized RBF neural network can achieve a recognition accuracy of 94.6%.
{"title":"Material Recognition Based on a Pulsed Time-of-Flight Camera","authors":"Jizhong Zhang, S. Lang, Qiang Wu, Chuan Liu","doi":"10.1109/ISPCE-CN48734.2019.8958633","DOIUrl":"https://doi.org/10.1109/ISPCE-CN48734.2019.8958633","url":null,"abstract":"This study presents a method for material recognition using a pulsed time-of-flight (ToF) camera. The method measures the material bidirectional reflectance distribution function (BRDF) as a feature for material recognition by a pulsed ToF camera. We use the measurements of incident light at different angles to form the BRDF feature vectors. The feature vectors are used to build a training and test set to train and validate a classifier to perform the recognition. We choose the radial basis function (RBF) neural network as a classifier based on the nonlinear characteristics of material BRDF. Finally, we construct a turntable-based measurement system and use the material BRDF as the feature for classifying a variety of materials including metals and plastics. The optimized RBF neural network can achieve a recognition accuracy of 94.6%.","PeriodicalId":221535,"journal":{"name":"2019 IEEE Symposium on Product Compliance Engineering - Asia (ISPCE-CN)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116909829","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}
Acoustic beamforming is an important technology in microphone array signal processing. It relates to the acquisition of speech signals by intelligent devices in complex environments. Acoustic beamforming is to form spatial directivity of microphone array, enhance desired signal, and suppress interference and noise. When the direction of desired signal is not accurately known, acoustic beamforming method like Frost beamforming would fail to filter interference and noise signals. This paper attempts to enhance the robustness of acoustic beamforming against inaccurate signal direction. Based on diagonal loading technique, an adaptive method is proposed to estimate signal direction. Simulation is performed on the basis of Frost beamforming method. The results show that the proposed adaptive diagonal loading method is able to suppress interference and noise signals. The signal to interference noise ratio is improved compared with non-adaptive method.
{"title":"Acoustic beamforming through adaptive diagonal loading","authors":"Xin Zhang, Luhao Zhuang, Wenwen Liu, Hao Qi, Xiu Zhang","doi":"10.1109/ISPCE-CN48734.2019.8958621","DOIUrl":"https://doi.org/10.1109/ISPCE-CN48734.2019.8958621","url":null,"abstract":"Acoustic beamforming is an important technology in microphone array signal processing. It relates to the acquisition of speech signals by intelligent devices in complex environments. Acoustic beamforming is to form spatial directivity of microphone array, enhance desired signal, and suppress interference and noise. When the direction of desired signal is not accurately known, acoustic beamforming method like Frost beamforming would fail to filter interference and noise signals. This paper attempts to enhance the robustness of acoustic beamforming against inaccurate signal direction. Based on diagonal loading technique, an adaptive method is proposed to estimate signal direction. Simulation is performed on the basis of Frost beamforming method. The results show that the proposed adaptive diagonal loading method is able to suppress interference and noise signals. The signal to interference noise ratio is improved compared with non-adaptive method.","PeriodicalId":221535,"journal":{"name":"2019 IEEE Symposium on Product Compliance Engineering - Asia (ISPCE-CN)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124410376","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 : 2019-10-01DOI: 10.1109/ISPCE-CN48734.2019.8958620
S. Mak, W. F. Tang, C. H. Li, W. H. Chiu, H. Chan, C. C. Lee
Traffic density on roads directly affects the arrival time of emergency services. Effective monitoring of traffic flow and shortly time of traffic control will help facilitate the arrival time of emergency services. In this paper, some traffic monitoring measurements systems are included. Vehicle tracking algorithms are one of the systems that can provide traffic data, and the system can be configured to project visual images for analysis. Congested transportation is a key issue in Hong Kong. Being able to collect traffic density data for analysis can provide effective and substantive data for sustainable development. To provide unobstructed traffic, thereby reducing lane density and reducing obstruction to emergency services. There are video processing methods to understand traffic conditions. These systems can only capture different traffic conditions to evaluate traffic details. But it cannot control traffic conditions.
{"title":"The Development of Smart Traffic Analysis System","authors":"S. Mak, W. F. Tang, C. H. Li, W. H. Chiu, H. Chan, C. C. Lee","doi":"10.1109/ISPCE-CN48734.2019.8958620","DOIUrl":"https://doi.org/10.1109/ISPCE-CN48734.2019.8958620","url":null,"abstract":"Traffic density on roads directly affects the arrival time of emergency services. Effective monitoring of traffic flow and shortly time of traffic control will help facilitate the arrival time of emergency services. In this paper, some traffic monitoring measurements systems are included. Vehicle tracking algorithms are one of the systems that can provide traffic data, and the system can be configured to project visual images for analysis. Congested transportation is a key issue in Hong Kong. Being able to collect traffic density data for analysis can provide effective and substantive data for sustainable development. To provide unobstructed traffic, thereby reducing lane density and reducing obstruction to emergency services. There are video processing methods to understand traffic conditions. These systems can only capture different traffic conditions to evaluate traffic details. But it cannot control traffic conditions.","PeriodicalId":221535,"journal":{"name":"2019 IEEE Symposium on Product Compliance Engineering - Asia (ISPCE-CN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130288703","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 : 2019-10-01DOI: 10.1109/ISPCE-CN48734.2019.8958634
Liu Yucheng, Wei Yang, Wang Hao, Koo Cheon Hoi, K. Tsang
Heart is one of the most significant organs of the human body. Nowadays, due to irregular work schedules and increasing life pressures, the incidence of heart diseases has gradually increased. According to the statistics of World Health organization (WHO), heart-related diseases have been the No. 1 killer with about 18 million death per year. In particular, a proportion of deaths is caused by the lack of effective heart monitoring and untimely aid. In order to reduce these avoidable tragedies, various wireless IoT technologies have been applied in smart heart monitoring systems. In this paper, a new collaborative NB-IoT structure-based heart monitoring scheme standardized by IEEE 1451 is presented to reduce the transmission latency and system development complexity.
{"title":"An IEEE 1451-Standardized Heart Monitoring Scheme based on Collaborative NB-IoT Structure","authors":"Liu Yucheng, Wei Yang, Wang Hao, Koo Cheon Hoi, K. Tsang","doi":"10.1109/ISPCE-CN48734.2019.8958634","DOIUrl":"https://doi.org/10.1109/ISPCE-CN48734.2019.8958634","url":null,"abstract":"Heart is one of the most significant organs of the human body. Nowadays, due to irregular work schedules and increasing life pressures, the incidence of heart diseases has gradually increased. According to the statistics of World Health organization (WHO), heart-related diseases have been the No. 1 killer with about 18 million death per year. In particular, a proportion of deaths is caused by the lack of effective heart monitoring and untimely aid. In order to reduce these avoidable tragedies, various wireless IoT technologies have been applied in smart heart monitoring systems. In this paper, a new collaborative NB-IoT structure-based heart monitoring scheme standardized by IEEE 1451 is presented to reduce the transmission latency and system development complexity.","PeriodicalId":221535,"journal":{"name":"2019 IEEE Symposium on Product Compliance Engineering - Asia (ISPCE-CN)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123057921","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 movie box office is now considered a relatively unpredictable short-term experience product. The profits of the film industry are constantly expanding, and more and more investors are engaged in it. But its uncertainty has caused huge losses for many investors. In this paper, film data from 1980 to 2018 were collected on box office mojo, and then, we use machine learning methods, including the Ensemble learning algorithm, to build a predictive model. Results show that the gradient boosting decision tree (GBDT) gives the best performance, of which R2 is higher than 0.995. Experimental results show that the Ensemble learning algorithm is much better than the traditional machine learning algorithm.
{"title":"Movie box office prediction based on ensemble learning","authors":"Shuangyan Wu, Yufan Zheng, Zhikang Lai, Fujian Wu, Choujun Zhan","doi":"10.1109/ISPCE-CN48734.2019.8958631","DOIUrl":"https://doi.org/10.1109/ISPCE-CN48734.2019.8958631","url":null,"abstract":"The movie box office is now considered a relatively unpredictable short-term experience product. The profits of the film industry are constantly expanding, and more and more investors are engaged in it. But its uncertainty has caused huge losses for many investors. In this paper, film data from 1980 to 2018 were collected on box office mojo, and then, we use machine learning methods, including the Ensemble learning algorithm, to build a predictive model. Results show that the gradient boosting decision tree (GBDT) gives the best performance, of which R2 is higher than 0.995. Experimental results show that the Ensemble learning algorithm is much better than the traditional machine learning algorithm.","PeriodicalId":221535,"journal":{"name":"2019 IEEE Symposium on Product Compliance Engineering - Asia (ISPCE-CN)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123429334","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 : 2018-12-01DOI: 10.1109/ISPCE-CN48734.2019.8958622
C. C. Lee, C. F. Lau, M. T. Kwan
In this paper, a critical study on the improvement of energy efficiency on the commercial light emitting diode (LED) driver along with the development of power conversion technique over the last two decades was conducted. A new classification of LED driver was proposed based on the new technologies and construction invented recently, and the past classifications of LED driver used. The corresponding energy efficiency on different types of LED drivers was studied accordingly. A new effective labeling scheme of energy efficiency on LED driver that will be suitable in Hong Kong from 2019 to 2029 was proposed based on the recent situation and the new classification. This proposed labelling scheme can be used as reference by the manufacturers of LED driver on the selection of power conversion techniques with various levels of energy efficiency.
{"title":"Critical Study on the Relationship between Power Conversion Technique and Energy Efficiency on LED driver","authors":"C. C. Lee, C. F. Lau, M. T. Kwan","doi":"10.1109/ISPCE-CN48734.2019.8958622","DOIUrl":"https://doi.org/10.1109/ISPCE-CN48734.2019.8958622","url":null,"abstract":"In this paper, a critical study on the improvement of energy efficiency on the commercial light emitting diode (LED) driver along with the development of power conversion technique over the last two decades was conducted. A new classification of LED driver was proposed based on the new technologies and construction invented recently, and the past classifications of LED driver used. The corresponding energy efficiency on different types of LED drivers was studied accordingly. A new effective labeling scheme of energy efficiency on LED driver that will be suitable in Hong Kong from 2019 to 2029 was proposed based on the recent situation and the new classification. This proposed labelling scheme can be used as reference by the manufacturers of LED driver on the selection of power conversion techniques with various levels of energy efficiency.","PeriodicalId":221535,"journal":{"name":"2019 IEEE Symposium on Product Compliance Engineering - Asia (ISPCE-CN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126991356","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：