Pub Date : 2017-07-01DOI: 10.1109/HSI.2017.8005030
Xiao-Li Chen, Qingshan Li, Yishuai Lin, B. Zhou
Meta-search engine is a comprehensive search tool, which is build base on those member search engines. All result entities reported by member search engines are merged into one ranked list according to their quality. It is well knowing that the core problem in meta-search engine is how to merge the results and provide user with a more effective rank list. This paper dealt with a synthesized merging algorithm by utilizing five features to estimate the quality of each result entity. For a returned result entity, we first record its' position of the original result list. Secondly, count the number of duplications. Thirdly, calculate the similarity between query terms and result content. Fourthly, get the capacity of the search members which will be called later. Fifth, analyze whether the current entity is in line with user's interests. Wherein users' interests are obtained both according to users' browsing history and feedback. Finally, we use the linear fusion model to merge the results set and re-ranking the results list. Experimental results shown that the merging method we proposed in this paper improved the accuracy and satisfaction degree in some cases compared with member search engines and several current meta-search engines.
{"title":"A synthesized method of result merging in meta-search engine","authors":"Xiao-Li Chen, Qingshan Li, Yishuai Lin, B. Zhou","doi":"10.1109/HSI.2017.8005030","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005030","url":null,"abstract":"Meta-search engine is a comprehensive search tool, which is build base on those member search engines. All result entities reported by member search engines are merged into one ranked list according to their quality. It is well knowing that the core problem in meta-search engine is how to merge the results and provide user with a more effective rank list. This paper dealt with a synthesized merging algorithm by utilizing five features to estimate the quality of each result entity. For a returned result entity, we first record its' position of the original result list. Secondly, count the number of duplications. Thirdly, calculate the similarity between query terms and result content. Fourthly, get the capacity of the search members which will be called later. Fifth, analyze whether the current entity is in line with user's interests. Wherein users' interests are obtained both according to users' browsing history and feedback. Finally, we use the linear fusion model to merge the results set and re-ranking the results list. Experimental results shown that the merging method we proposed in this paper improved the accuracy and satisfaction degree in some cases compared with member search engines and several current meta-search engines.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125534053","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005043
Simone Guasconi, M. Porta, Cristiano Resta, C. Rottenbacher
We present an eye tracking system developed to study the driver's gaze behavior while driving a car. Two main challenges distinguish this project from similar works with analogous purposes: (1) the use of a cheap portable remote eye tracker, normally employed for indoor applications in controlled light conditions; and (2) the use of an ordinary webcam to shoot the road in front of the car. The purpose is to generate a video where the driver's fixations are graphically and dynamically superimposed on the road shot by webcam (taking into account the different viewpoints of driver and camera). The carried-out experiments confirmed that the implemented system, while perfectible, fulfills the requirements initially set.
{"title":"A low-cost implementation of an eye tracking system for driver's gaze analysis","authors":"Simone Guasconi, M. Porta, Cristiano Resta, C. Rottenbacher","doi":"10.1109/HSI.2017.8005043","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005043","url":null,"abstract":"We present an eye tracking system developed to study the driver's gaze behavior while driving a car. Two main challenges distinguish this project from similar works with analogous purposes: (1) the use of a cheap portable remote eye tracker, normally employed for indoor applications in controlled light conditions; and (2) the use of an ordinary webcam to shoot the road in front of the car. The purpose is to generate a video where the driver's fixations are graphically and dynamically superimposed on the road shot by webcam (taking into account the different viewpoints of driver and camera). The carried-out experiments confirmed that the implemented system, while perfectible, fulfills the requirements initially set.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125835449","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005006
V. U. Tjhin, Anita Rahayu, Kiky Soraya
This study aimed to determine the importance of an online forum discussion in online learning. To advance the function of the online forum discussion in online learning, it needs a model of effective collaborative learning. That advancement will also upsurge the success of online learning in Indonesia. However, collaborative learning has many challenges in distance learning. Students are required to have good time management, have the ability on self-learning, as well as active in the online discussion forums. This research had been conducted on students of Business Management department in distance education program. The overall results showed that the activity of the individual tasks and task groups, the presence in video conferencing, active in online discussion forums, and the readiness to take the quiz online, it has a significant relationship to student performance.
{"title":"Evaluating the performance of students through collaborative learning: Case study: Distance education program in Indonesia","authors":"V. U. Tjhin, Anita Rahayu, Kiky Soraya","doi":"10.1109/HSI.2017.8005006","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005006","url":null,"abstract":"This study aimed to determine the importance of an online forum discussion in online learning. To advance the function of the online forum discussion in online learning, it needs a model of effective collaborative learning. That advancement will also upsurge the success of online learning in Indonesia. However, collaborative learning has many challenges in distance learning. Students are required to have good time management, have the ability on self-learning, as well as active in the online discussion forums. This research had been conducted on students of Business Management department in distance education program. The overall results showed that the activity of the individual tasks and task groups, the presence in video conferencing, active in online discussion forums, and the readiness to take the quiz online, it has a significant relationship to student performance.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124833660","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 : 2017-07-01DOI: 10.1109/HSI.2017.8004989
Krzysztof Czuszyński, J. Rumiński, J. Wtorek
Gesture sensors for mobile devices, which have a capability of distinguishing hand poses, require efficient and accurate classifiers in order to recognize gestures based on the sequences of primitives. Two methods of poses recognition for the optical linear sensor were proposed and validated. The Gaussian distribution fitting and Artificial Neural Network based methods represent two kinds of classification approaches. Three types of hand poses, differing in the number of fingers joined together, were investigated. The reflected light intensity pattern originated by hand located closely to the sensor was parameterized into 14 features. The change of reflection pattern originated by hand dislocation was reduced by application of two variable functions in the first of the methods. A one and two hidden layers topologies were considered in the neural network related approach. Both methods were designed with the use of a training set of samples and validated with another (testing) set. The results present the average poses recognition rate of 81.19% for Gaussian distribution fitting and 90.02% for ANN based method.
{"title":"Pose classification in the gesture recognition using the linear optical sensor","authors":"Krzysztof Czuszyński, J. Rumiński, J. Wtorek","doi":"10.1109/HSI.2017.8004989","DOIUrl":"https://doi.org/10.1109/HSI.2017.8004989","url":null,"abstract":"Gesture sensors for mobile devices, which have a capability of distinguishing hand poses, require efficient and accurate classifiers in order to recognize gestures based on the sequences of primitives. Two methods of poses recognition for the optical linear sensor were proposed and validated. The Gaussian distribution fitting and Artificial Neural Network based methods represent two kinds of classification approaches. Three types of hand poses, differing in the number of fingers joined together, were investigated. The reflected light intensity pattern originated by hand located closely to the sensor was parameterized into 14 features. The change of reflection pattern originated by hand dislocation was reduced by application of two variable functions in the first of the methods. A one and two hidden layers topologies were considered in the neural network related approach. Both methods were designed with the use of a training set of samples and validated with another (testing) set. The results present the average poses recognition rate of 81.19% for Gaussian distribution fitting and 90.02% for ANN based method.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123134941","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005051
Andreas Akun, W. Andreani
This article studies nomophobia as a modern psychological attachment to smartphone as studied through Mophie advertisement “All Powerless”. Studies have shown that most youngsters suffer nomophobia to a certain degree ranging from mild to severe. In Indonesia, all studied participants are nomophobic with 71.42% suffer moderate nomophobia, 19.04% severe and 9.52% mild. Through the psychosemiotic study of nomophobia in the ad, it is concluded that beyond the surface denotative meaning that the ad is designed to simultaneously invite consumers to buy it and legitimize the disappearance of nomophobia, the deeper ideological meaning has surfaced: people have been psychologically attached too much to the very technology than to other human beings and God, signifying all are powerless in the face of technology.
{"title":"Powerfully tecnologized, powerlessly connected: The psychosemiotics of nomophobia","authors":"Andreas Akun, W. Andreani","doi":"10.1109/HSI.2017.8005051","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005051","url":null,"abstract":"This article studies nomophobia as a modern psychological attachment to smartphone as studied through Mophie advertisement “All Powerless”. Studies have shown that most youngsters suffer nomophobia to a certain degree ranging from mild to severe. In Indonesia, all studied participants are nomophobic with 71.42% suffer moderate nomophobia, 19.04% severe and 9.52% mild. Through the psychosemiotic study of nomophobia in the ad, it is concluded that beyond the surface denotative meaning that the ad is designed to simultaneously invite consumers to buy it and legitimize the disappearance of nomophobia, the deeper ideological meaning has surfaced: people have been psychologically attached too much to the very technology than to other human beings and God, signifying all are powerless in the face of technology.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123046072","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005025
N. Iswari, Wella, Ranny
Development of local fruit industry in Indonesia is very high, but less competitive than imported fruits. Produced fruit kinds in this country is very diverse, but the use of technology to support the production and distribution is still not widely applied. This makes the local fruit market less competitive than imported fruits that has largely been applying technology production support. In this research, we analyse the relationship between fruit digital image and sweetness level of it. Image processing method carried out to prepare a digital image that is ready to be processed in the matching stage. K-Nearest Neighbor method is used to match fruit digital image with its sweetness levels. Sweetness levels were measured using Brix degrees' units. Matching results would be useful to predict fruit ripeness based on digital image, so that the conventional measurement methods that should spoil the fruit can be handled. Experiments were performed in several types of fruits include: bananas, apples and melons. Each of these fruit image is recorded from several difference angles. We also measured levels of sweetness using a sweetness measuring instrument, called refractometer. Both of these will become the training materials for classification system and then performed using kNN. The resulting method of this research is implemented in the application, named Fruitylicious.
{"title":"Fruitylicious: Mobile application for fruit ripeness determination based on fruit image","authors":"N. Iswari, Wella, Ranny","doi":"10.1109/HSI.2017.8005025","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005025","url":null,"abstract":"Development of local fruit industry in Indonesia is very high, but less competitive than imported fruits. Produced fruit kinds in this country is very diverse, but the use of technology to support the production and distribution is still not widely applied. This makes the local fruit market less competitive than imported fruits that has largely been applying technology production support. In this research, we analyse the relationship between fruit digital image and sweetness level of it. Image processing method carried out to prepare a digital image that is ready to be processed in the matching stage. K-Nearest Neighbor method is used to match fruit digital image with its sweetness levels. Sweetness levels were measured using Brix degrees' units. Matching results would be useful to predict fruit ripeness based on digital image, so that the conventional measurement methods that should spoil the fruit can be handled. Experiments were performed in several types of fruits include: bananas, apples and melons. Each of these fruit image is recorded from several difference angles. We also measured levels of sweetness using a sweetness measuring instrument, called refractometer. Both of these will become the training materials for classification system and then performed using kNN. The resulting method of this research is implemented in the application, named Fruitylicious.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126725324","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005009
J. Luke, Kiky Soraya
Delivering persuasive presentation is a challenging task for the university students. One of the difficult parts is grasping the attention of audiences during the critical situations, such as in the early morning or after the lunch break. At the situations, students are not paying more attention to any speeches or presentations occurred in the classroom because of some lapses of attention span such as poor listening, yawns, blurred visual images, and noisy situations. For that reasons, the study seeks to investigate the most preferred SCREAM Rhetorical devices used by male and female students when doing persuasive presentation and verify whether gender differences play a role in the way the male and female students exploited SCREAM Rhetorical devices to persuade the audiences. To explore the application of SCREAM Rhetorical devices, this study involved sixteen English Business Presentation students; eight males and eight females who were randomly selected to record the business presentation in video as multimedia learning device. Then, the presentations through the videos were analyzed using Windingland (2012) SCREAM taxonomy that comprises Rhetorical devices into six types: Simile, Contrast, Rhyme, Echo, Alliteration, and Metaphor. The significant findings proved that the presentations displayed on the videos showed that all respondents executed SCREAM Rhetorical devices. The gender differences influenced the SCREAM rhetorical devices used. Interestingly, of six devices, Echo is the most preferred device exploited in the students' persuasive presentation.
{"title":"Gender differences in the use of SCREAM Rhetorical devices displayed on video presentations: (An analysis of undergraduate students' persuasive presentations)","authors":"J. Luke, Kiky Soraya","doi":"10.1109/HSI.2017.8005009","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005009","url":null,"abstract":"Delivering persuasive presentation is a challenging task for the university students. One of the difficult parts is grasping the attention of audiences during the critical situations, such as in the early morning or after the lunch break. At the situations, students are not paying more attention to any speeches or presentations occurred in the classroom because of some lapses of attention span such as poor listening, yawns, blurred visual images, and noisy situations. For that reasons, the study seeks to investigate the most preferred SCREAM Rhetorical devices used by male and female students when doing persuasive presentation and verify whether gender differences play a role in the way the male and female students exploited SCREAM Rhetorical devices to persuade the audiences. To explore the application of SCREAM Rhetorical devices, this study involved sixteen English Business Presentation students; eight males and eight females who were randomly selected to record the business presentation in video as multimedia learning device. Then, the presentations through the videos were analyzed using Windingland (2012) SCREAM taxonomy that comprises Rhetorical devices into six types: Simile, Contrast, Rhyme, Echo, Alliteration, and Metaphor. The significant findings proved that the presentations displayed on the videos showed that all respondents executed SCREAM Rhetorical devices. The gender differences influenced the SCREAM rhetorical devices used. Interestingly, of six devices, Echo is the most preferred device exploited in the students' persuasive presentation.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114724220","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005005
Febrianti Widyahastuti, Dendy Fransiskus, V. U. Tjhin
Edmodo called as ‘Facebook for schools’ [1] enable the academic social network site connecting students and teachers anywhere and anytime. It can be used to encourage students to complete activities assigned by teachers such as assignment and quiz posting, polls conducting, badges awarding, learning materials uploading, classroom discussions, grade tracking, and comments writing besides as personal digital library connected to Google drive, OneDrive, and much more. Accordingly, this paper provided a general overview of how students in class IX to XII of technology information and communication course fully participate in Edmodo. The main beneficial point of this research was the trend and analysis of K-12 students' participation at high school in Indonesia. Investigating the participation and factors underlying the students' patterns of behavior in Edmodo can provide guidelines for sustainable improvement of online learning management systems. The data analysis revealed that a high number of students join as members in Edmodo and only a few of them were not engaged due to limited access of internet. It was found that most of students in class XII-IPA were active in posting their assignments through Edmodo after school and that most dominant is class X. There were some discussions and sharing information between teacher-students and students-students related to the inside and outside classroom activities. The result also indicated that students in class XII were more active than those in class IX, X, and XI. Students of class XII are in the final year before joining universities. Thus, they were more serious about their study. Furthermore, the students found Edmodo as a communication tool and a user-friendly social learning platform enabling them to connect with classmates and teachers in online class. The results also inspired teachers to motivate and encourage the students' to do their best in the study and build a strong relationship inside and outside the class.
{"title":"How active are K-12 students using Edmodo as online motivation, interaction and collaboration tools for learning process?","authors":"Febrianti Widyahastuti, Dendy Fransiskus, V. U. Tjhin","doi":"10.1109/HSI.2017.8005005","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005005","url":null,"abstract":"Edmodo called as ‘Facebook for schools’ [1] enable the academic social network site connecting students and teachers anywhere and anytime. It can be used to encourage students to complete activities assigned by teachers such as assignment and quiz posting, polls conducting, badges awarding, learning materials uploading, classroom discussions, grade tracking, and comments writing besides as personal digital library connected to Google drive, OneDrive, and much more. Accordingly, this paper provided a general overview of how students in class IX to XII of technology information and communication course fully participate in Edmodo. The main beneficial point of this research was the trend and analysis of K-12 students' participation at high school in Indonesia. Investigating the participation and factors underlying the students' patterns of behavior in Edmodo can provide guidelines for sustainable improvement of online learning management systems. The data analysis revealed that a high number of students join as members in Edmodo and only a few of them were not engaged due to limited access of internet. It was found that most of students in class XII-IPA were active in posting their assignments through Edmodo after school and that most dominant is class X. There were some discussions and sharing information between teacher-students and students-students related to the inside and outside classroom activities. The result also indicated that students in class XII were more active than those in class IX, X, and XI. Students of class XII are in the final year before joining universities. Thus, they were more serious about their study. Furthermore, the students found Edmodo as a communication tool and a user-friendly social learning platform enabling them to connect with classmates and teachers in online class. The results also inspired teachers to motivate and encourage the students' to do their best in the study and build a strong relationship inside and outside the class.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120898265","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005052
R. Chairiyani, Erni Herawati, R. Widayanti
Mass Media have been acknowledged as a mean to shape the way people view the world. It indeed constructs the individual and social world. The evolution of human thinking is always changing as the development of media technology. Human creates communication technology as a tool to overcome the obstacles in communication. However, these tools are eventually shape human perspective to view the world. One of the content that people can see in mass media is culture. It spread massively through various mass media as a product and content. Through the mass media people can see other culture. From the culture they have seen in mass media, they eventually construct their own culture. One of the culture they have formed is cosplay. Therefore, this research is questioning about to what extent the mass media role had construct the reality of self-identity and social world of cosplayer. Secondly, how mass media had developed the hyper reality of cosplayer which it's reflected in cosplayer behavior. This paper had done with qualitative analysis. It means that the analysis did from the beginning until the end of the research. The result of this research shows that mass media, especially of video game and film have significant role to develop the cosplayer hyper-reality and identity. Those bring the cosplayer choose the character that represents their self-identity to play. Through this new identity, cosplayer forms the community to share their experience.
{"title":"The role of Mass Media to construct cosplayer self identity, social reality and hyper reality","authors":"R. Chairiyani, Erni Herawati, R. Widayanti","doi":"10.1109/HSI.2017.8005052","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005052","url":null,"abstract":"Mass Media have been acknowledged as a mean to shape the way people view the world. It indeed constructs the individual and social world. The evolution of human thinking is always changing as the development of media technology. Human creates communication technology as a tool to overcome the obstacles in communication. However, these tools are eventually shape human perspective to view the world. One of the content that people can see in mass media is culture. It spread massively through various mass media as a product and content. Through the mass media people can see other culture. From the culture they have seen in mass media, they eventually construct their own culture. One of the culture they have formed is cosplay. Therefore, this research is questioning about to what extent the mass media role had construct the reality of self-identity and social world of cosplayer. Secondly, how mass media had developed the hyper reality of cosplayer which it's reflected in cosplayer behavior. This paper had done with qualitative analysis. It means that the analysis did from the beginning until the end of the research. The result of this research shows that mass media, especially of video game and film have significant role to develop the cosplayer hyper-reality and identity. Those bring the cosplayer choose the character that represents their self-identity to play. Through this new identity, cosplayer forms the community to share their experience.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"184 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132246599","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 : 2017-07-01DOI: 10.1109/HSI.2017.8004991
J. Dembski, J. Rumiński
This paper presents 2D image processing approach to playback detection in automatic speaker verification (ASV) systems using spectrograms as speech signal representation. Three feature extraction and classification methods: histograms of oriented gradients (HOG) with support vector machines (SVM), HAAR wavelets with AdaBoost classifier and deep convolutional neural networks (CNN) were compared on different data partitions in respect of speakers or playback devices: for instance with different speakers in training and test subsets. The playback detection systems were trained and tested on two speech datasets S1 and S2 manufactured independently by two different institutions. The test error for both datasets oscillates about the level of 1% for HOG+SVM and even below it for CNN in bigger S1 base. In cross validation scenario in which one base was used for training and second base for the test the results were very poor what suggests that the information relevant for playback detection appeared in each base in different way.
{"title":"Playback detection using machine learning with spectrogram features approach","authors":"J. Dembski, J. Rumiński","doi":"10.1109/HSI.2017.8004991","DOIUrl":"https://doi.org/10.1109/HSI.2017.8004991","url":null,"abstract":"This paper presents 2D image processing approach to playback detection in automatic speaker verification (ASV) systems using spectrograms as speech signal representation. Three feature extraction and classification methods: histograms of oriented gradients (HOG) with support vector machines (SVM), HAAR wavelets with AdaBoost classifier and deep convolutional neural networks (CNN) were compared on different data partitions in respect of speakers or playback devices: for instance with different speakers in training and test subsets. The playback detection systems were trained and tested on two speech datasets S1 and S2 manufactured independently by two different institutions. The test error for both datasets oscillates about the level of 1% for HOG+SVM and even below it for CNN in bigger S1 base. In cross validation scenario in which one base was used for training and second base for the test the results were very poor what suggests that the information relevant for playback detection appeared in each base in different way.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"164 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132273428","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：