Pub Date : 2013-11-01DOI: 10.1109/ICAWST.2013.6765434
Daria Vazhenina, K. Markov
The Russian language is characterized by very flexible word order, which limits the ability of the standard n-grams to capture important regularities in the data. Moreover, Russian is highly inflectional language with rich morphology, which leads to high out-of-vocabulary word rates. Recently factored language model (FLM) was proposed with the aim of addressing the problems of morphologically rich languages. In this paper, we describe our implementation of the FLM for the Russian language automatic speech recognition (ASR). We investigated the effect of different factors, and propose a strategy to find the best factor set and back-off path. Evaluation experiments showed that FLM can decrease the perplexity as much as 20%. This allows to achieve 4.0% word error rate (WER) relative reduction, which further increases to 6.9% when FLM is interpolated with the conventional 3-gram LM.
{"title":"Factored language modeling for Russian LVCSR","authors":"Daria Vazhenina, K. Markov","doi":"10.1109/ICAWST.2013.6765434","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765434","url":null,"abstract":"The Russian language is characterized by very flexible word order, which limits the ability of the standard n-grams to capture important regularities in the data. Moreover, Russian is highly inflectional language with rich morphology, which leads to high out-of-vocabulary word rates. Recently factored language model (FLM) was proposed with the aim of addressing the problems of morphologically rich languages. In this paper, we describe our implementation of the FLM for the Russian language automatic speech recognition (ASR). We investigated the effect of different factors, and propose a strategy to find the best factor set and back-off path. Evaluation experiments showed that FLM can decrease the perplexity as much as 20%. This allows to achieve 4.0% word error rate (WER) relative reduction, which further increases to 6.9% when FLM is interpolated with the conventional 3-gram LM.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"108 1","pages":"205-211"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77290010","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765525
Chih-Lin Hu, Pin-chun Chiu
The study of data dissemination with social relationship in delay-tolerant networks can be significant from the perspective of technical novelty and performance. This paper adopts the time-variant community mobility model to formulate the relationship between user mobility and social community in delay-tolerant networks. With synthetic trace data of various user mobility and community patterns, simulation results show that the proposed model is able to interpret many characteristics of movement behavior and social community structure, accordingly, with a friendly graphic presentation. Therefore, the proposed analysis model can be applied to facilitate the design of social-based data dissemination mechanisms in delay-tolerant networks.
{"title":"Analyzing the influence of mobile social communities on data dissemination in delay-tolerant networks","authors":"Chih-Lin Hu, Pin-chun Chiu","doi":"10.1109/ICAWST.2013.6765525","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765525","url":null,"abstract":"The study of data dissemination with social relationship in delay-tolerant networks can be significant from the perspective of technical novelty and performance. This paper adopts the time-variant community mobility model to formulate the relationship between user mobility and social community in delay-tolerant networks. With synthetic trace data of various user mobility and community patterns, simulation results show that the proposed model is able to interpret many characteristics of movement behavior and social community structure, accordingly, with a friendly graphic presentation. Therefore, the proposed analysis model can be applied to facilitate the design of social-based data dissemination mechanisms in delay-tolerant networks.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"457 1","pages":"685-691"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76692327","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765523
Abdurhman Albasir, S. Naik, T. Abdunabi
Mobile web browsing is one of the most commonly used and wide-spread application (app) among smartphone apps. However, the complexity of web-pages is increasing especially if the web-pages are designed for desktop computers. The existence of advertisements (ads) in web-page leads to even higher complexity of the web-pages. This complexity in smartphone's environment where the resources are limited (e.g., battery and bandwidth) is reflected in longer loading time, more energy consumed, and more bytes transferred. In this paper, we classify the web contents into: (i) core information, and (ii) forced "unwanted" information, namely ads. Then, we evaluate resources used for web advertising. Based on the measurements of the cost of web advertising, we propose a framework for mobile browsing that adapts the web-pages delivered to the smartphone, based on the smartphone's current battery level and the network type. The adaptation of the web content is in the form of controlling the amount of ads to be displayed on the web-page. Our system aims to (i) extend smartphone battery life and (ii) preserve the bandwidth needed to download the web-pages while balancing the satisfaction of the publishers of web-pages as well as the end users.
{"title":"Smart mobile web browsing","authors":"Abdurhman Albasir, S. Naik, T. Abdunabi","doi":"10.1109/ICAWST.2013.6765523","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765523","url":null,"abstract":"Mobile web browsing is one of the most commonly used and wide-spread application (app) among smartphone apps. However, the complexity of web-pages is increasing especially if the web-pages are designed for desktop computers. The existence of advertisements (ads) in web-page leads to even higher complexity of the web-pages. This complexity in smartphone's environment where the resources are limited (e.g., battery and bandwidth) is reflected in longer loading time, more energy consumed, and more bytes transferred. In this paper, we classify the web contents into: (i) core information, and (ii) forced \"unwanted\" information, namely ads. Then, we evaluate resources used for web advertising. Based on the measurements of the cost of web advertising, we propose a framework for mobile browsing that adapts the web-pages delivered to the smartphone, based on the smartphone's current battery level and the network type. The adaptation of the web content is in the form of controlling the amount of ads to be displayed on the web-page. Our system aims to (i) extend smartphone battery life and (ii) preserve the bandwidth needed to download the web-pages while balancing the satisfaction of the publishers of web-pages as well as the end users.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"7 1","pages":"671-679"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84845891","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765480
Li-Hong Juang, Ming-Ni Wu
Nowadays medical technology makes the inevitable trend of an ageing population. So intelligent home care is an important direction of development of science and technology, in particular, elderly in-home safety management issues become more and more important. In this research, we propose a low of operation algorithm and use the triangular pattern rule, then can quickly detect abnormal movements of humanoid by the installation of a robot with camera vision at home that will be able to judge the abnormal movements of in-home elderly in real time. In this research, we will present a preliminary design and experimental results of abnormal movements from body posture that utilizes image pre-processing and three triangular-mass-central points to extract the characteristics. The result shows that the proposed method would adopt the few characteristic value and the accuracy can reach to 90% a single character posture. Furthermore the accuracy can be up to 100% when a continuous-time sampling criterion and support vector machine (SVM) classifier are taken.
{"title":"Abnormal action tracking using robot vision system","authors":"Li-Hong Juang, Ming-Ni Wu","doi":"10.1109/ICAWST.2013.6765480","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765480","url":null,"abstract":"Nowadays medical technology makes the inevitable trend of an ageing population. So intelligent home care is an important direction of development of science and technology, in particular, elderly in-home safety management issues become more and more important. In this research, we propose a low of operation algorithm and use the triangular pattern rule, then can quickly detect abnormal movements of humanoid by the installation of a robot with camera vision at home that will be able to judge the abnormal movements of in-home elderly in real time. In this research, we will present a preliminary design and experimental results of abnormal movements from body posture that utilizes image pre-processing and three triangular-mass-central points to extract the characteristics. The result shows that the proposed method would adopt the few characteristic value and the accuracy can reach to 90% a single character posture. Furthermore the accuracy can be up to 100% when a continuous-time sampling criterion and support vector machine (SVM) classifier are taken.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"24 1","pages":"438-444"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89081739","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765487
Chuan-Feng Chiu, S. J. Hsu, S. Jan
In past years, Cloud computing is gained more attention in industry and academic area. The advance technologies are needed to match the demand of the development of cloud computing. MapReduce is one of the enabling technology. MapReduce is a programming model supporting parallel computation especially for data-intensive cloud computing applications. However, MapReduce needs a master node to coordinate the execution of the parallel computation. This may cause communication bottleneck and single point of failure error. Therefore, in this paper we propose a distributed MapReduce framework based on Distributed Hash Tables to support large scale cloud computing applications.
{"title":"Distributed MapReduce framework using distributed hash table","authors":"Chuan-Feng Chiu, S. J. Hsu, S. Jan","doi":"10.1109/ICAWST.2013.6765487","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765487","url":null,"abstract":"In past years, Cloud computing is gained more attention in industry and academic area. The advance technologies are needed to match the demand of the development of cloud computing. MapReduce is one of the enabling technology. MapReduce is a programming model supporting parallel computation especially for data-intensive cloud computing applications. However, MapReduce needs a master node to coordinate the execution of the parallel computation. This may cause communication bottleneck and single point of failure error. Therefore, in this paper we propose a distributed MapReduce framework based on Distributed Hash Tables to support large scale cloud computing applications.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"38 1","pages":"475-481"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76149384","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765496
J. Jaudon, John Gobron
Investment in healthcare information technology (HIT) in the United States has grown drastically in recent years, but despite significant investment, clinician satisfaction with HIT remains low. High risks, conflicting interests, and regulatory hurdles make healthcare a daunting environment in which to introduce change, and benefits from increased spend have yet to be realized. In this paper we present an approach to implementing awareness computing in healthcare, to orchestrate the environment for clinicians and gain computing, power, and workflow efficiencies in many areas. The solution couples a unifying communications protocol with a distributed network of "aware units"-each capable of functioning in disparate systems - all communicating with centralized data gathering and logic processing core. The system is capable of delivering an intelligently orchestrated (i.e., "awareness") computing experience to users, even as they use systems never designed to interoperate. This system is currently in use in hospitals across the US, and advanced features are being tested in hospital pilot projects and in partnerships with academic medical centers.
{"title":"Advancement in clinician efficiency through awareness computing","authors":"J. Jaudon, John Gobron","doi":"10.1109/ICAWST.2013.6765496","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765496","url":null,"abstract":"Investment in healthcare information technology (HIT) in the United States has grown drastically in recent years, but despite significant investment, clinician satisfaction with HIT remains low. High risks, conflicting interests, and regulatory hurdles make healthcare a daunting environment in which to introduce change, and benefits from increased spend have yet to be realized. In this paper we present an approach to implementing awareness computing in healthcare, to orchestrate the environment for clinicians and gain computing, power, and workflow efficiencies in many areas. The solution couples a unifying communications protocol with a distributed network of \"aware units\"-each capable of functioning in disparate systems - all communicating with centralized data gathering and logic processing core. The system is capable of delivering an intelligently orchestrated (i.e., \"awareness\") computing experience to users, even as they use systems never designed to interoperate. This system is currently in use in hospitals across the US, and advanced features are being tested in hospital pilot projects and in partnerships with academic medical centers.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"1 1","pages":"524-530"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83497624","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765504
Xudong Mao, Yanghui Rao, Qing Li
In social based Web services systems, some resources gain popularity while others do not. It would be valuable if we can predict the popularity of certain resource. In this work, we study the recipe popularity prediction problem using the Yelp dataset. We investigate various features that can be extracted and help to improve the performance. In particular, we propose to do the sentiment analysis over the reviews and treat the sentimental scores as one of the features. A polynomial regression model is developed to predict the recipe popularity. The experimental results show that our proposed method outperforms the baseline method.
{"title":"Recipe popularity prediction based on the analysis of social reviews","authors":"Xudong Mao, Yanghui Rao, Qing Li","doi":"10.1109/ICAWST.2013.6765504","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765504","url":null,"abstract":"In social based Web services systems, some resources gain popularity while others do not. It would be valuable if we can predict the popularity of certain resource. In this work, we study the recipe popularity prediction problem using the Yelp dataset. We investigate various features that can be extracted and help to improve the performance. In particular, we propose to do the sentiment analysis over the reviews and treat the sentimental scores as one of the features. A polynomial regression model is developed to predict the recipe popularity. The experimental results show that our proposed method outperforms the baseline method.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"294 1","pages":"568-573"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86447820","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}
Environment sensing systems and positioning systems such as GPS (Global Positioning System) are requirements for logistics supply chains, especially refrigerated cargo systems that require environment sensing data. In this paper, we state our system requirements and compare our proposed solution with other existing solutions. Our proposed system focuses on the cold chain tracking system to provide locations of vehicles and monitor the temperature of refrigerated cargo carried by the vehicles. The system includes Android phones with GPS module on the vehicles, a website for the visual control by using Google Map API, and a web service acts as a bridge between Android phones and database.
{"title":"Design of refrigerated cargo tracking systems","authors":"Jen-Yung Lin, Tuan-Anh Do, Bo-Kai Yang, Yung-Fa Huang","doi":"10.1109/ICAWST.2013.6765473","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765473","url":null,"abstract":"Environment sensing systems and positioning systems such as GPS (Global Positioning System) are requirements for logistics supply chains, especially refrigerated cargo systems that require environment sensing data. In this paper, we state our system requirements and compare our proposed solution with other existing solutions. Our proposed system focuses on the cold chain tracking system to provide locations of vehicles and monitor the temperature of refrigerated cargo carried by the vehicles. The system includes Android phones with GPS module on the vehicles, a website for the visual control by using Google Map API, and a web service acts as a bridge between Android phones and database.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"34 1","pages":"400-406"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86433958","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765430
Akira Saji, K. Tanno, Jie Huang
Recently, we have proposed a 3-D sound system using horizontal arrange loudspeakers by combine the effect of HRTF and the amplitude panning method. In that system, loudspeakers are set at the height of subject's ear level and its sweet-spot is limited by the height of loudspeakers. When listener's ear level is different with loudspeakers, it will cause difficulty of sound localization or breakdown of sound localization. However, it is difficult to adjust properly both the height of loudspeakers and subject's ear level every time. In this paper, we aimed to improve the robustness of the 3-D sound system using vertical loudspeakers array. As a result of experiments, we verify that the loudspeaker arrays can improve the robustness of the 3-D sound system.
{"title":"Improve vertical sweet-spot of 3-D sound system by loudspeaker arrays","authors":"Akira Saji, K. Tanno, Jie Huang","doi":"10.1109/ICAWST.2013.6765430","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765430","url":null,"abstract":"Recently, we have proposed a 3-D sound system using horizontal arrange loudspeakers by combine the effect of HRTF and the amplitude panning method. In that system, loudspeakers are set at the height of subject's ear level and its sweet-spot is limited by the height of loudspeakers. When listener's ear level is different with loudspeakers, it will cause difficulty of sound localization or breakdown of sound localization. However, it is difficult to adjust properly both the height of loudspeakers and subject's ear level every time. In this paper, we aimed to improve the robustness of the 3-D sound system using vertical loudspeakers array. As a result of experiments, we verify that the loudspeaker arrays can improve the robustness of the 3-D sound system.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"15 1","pages":"179-183"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82606722","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765417
A. Takeuchi, Y. Manabe, K. Sugawara
In the last decade, soft biometric traits have emerged as more convenient and non-intrusive alternatives for person authentication task. However a soft biometric trait cannot be a main feature for person authentication because it lacks distinctiveness compared with fingerprint, palm vein pattern and so on. Therefore this study proposes a person verification method integrating handwriting motion in the air and a shape of a hand, which can be successively measured by a device (RGB and depth camera). As the result of person verification experiment for 10 subjects, we obtained a good verification performance that FAR is 2% when FRR is 0%.
{"title":"Multimodal soft biometrie verification by hand shape and handwriting motion in the air","authors":"A. Takeuchi, Y. Manabe, K. Sugawara","doi":"10.1109/ICAWST.2013.6765417","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765417","url":null,"abstract":"In the last decade, soft biometric traits have emerged as more convenient and non-intrusive alternatives for person authentication task. However a soft biometric trait cannot be a main feature for person authentication because it lacks distinctiveness compared with fingerprint, palm vein pattern and so on. Therefore this study proposes a person verification method integrating handwriting motion in the air and a shape of a hand, which can be successively measured by a device (RGB and depth camera). As the result of person verification experiment for 10 subjects, we obtained a good verification performance that FAR is 2% when FRR is 0%.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"93 1","pages":"103-109"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83881494","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：