The importance of researches in the old days is the retrieval of similar objects. Content-Based Image Retrieval (CBIR) system uses low-level features such as texture, color, and shape to extract the features, but when it comes to food images it is hard to get satisfactory accurate results. Recognition of food images has recently become very important and challenging due to people's health care, religious or cultural reasons. In this paper, we propose a system that recognizes small food images consist of 10 categories by using bag of features (BoF) based on SURF detection features. In addition, we achieved up to 78% accuracy rate, and try to improve the feature detection by using color features at the same time with the SURF feature detection. This experiment shows that more accurate rate of results will be obtained than the existing methods.
在过去，研究的重要性在于检索相似的对象。基于内容的图像检索(Content-Based Image Retrieval, CBIR)系统利用纹理、颜色、形状等底层特征来提取食物图像的特征，但当涉及到食物图像时，很难得到令人满意的准确结果。由于人们的医疗保健、宗教或文化原因，食物图像的识别最近变得非常重要和具有挑战性。本文提出了一种基于SURF检测特征的特征袋(bag of features, BoF)识别10类小食品图像的系统。此外，我们实现了高达78%的准确率，并尝试在SURF特征检测的同时使用颜色特征来改进特征检测。实验表明，与现有方法相比，该方法的结果准确率更高。
{"title":"Food Image Recognition by Using Bag of SURF: Color Features","authors":"Alameri Abdulrahman, T. Ozeki","doi":"10.1145/2814940.2814976","DOIUrl":"https://doi.org/10.1145/2814940.2814976","url":null,"abstract":"The importance of researches in the old days is the retrieval of similar objects. Content-Based Image Retrieval (CBIR) system uses low-level features such as texture, color, and shape to extract the features, but when it comes to food images it is hard to get satisfactory accurate results. Recognition of food images has recently become very important and challenging due to people's health care, religious or cultural reasons. In this paper, we propose a system that recognizes small food images consist of 10 categories by using bag of features (BoF) based on SURF detection features. In addition, we achieved up to 78% accuracy rate, and try to improve the feature detection by using color features at the same time with the SURF feature detection. This experiment shows that more accurate rate of results will be obtained than the existing methods.","PeriodicalId":427567,"journal":{"name":"Proceedings of the 3rd International Conference on Human-Agent Interaction","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115810963","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}
Hyewon Lee, Hyemee Kang, Sonya S. Kwak, Jaeryoung Lee, Min-Gyu Kim, Jun-Beom Kwon
In this article, we present two robot design types: human-like and product-like robot. A human-like robot is designed to be similar to humans in the appearance or behavior. A product-like robot is designed to maximize the functionality of a product. As well as the comparison between the human-like robot and product-like robot, cultural differences between Korea and Japan on perceived intellectual capability, robot-likeness, usefulness, overall impression and purchase intention were investigated. People evaluated the intellectual capability, usefulness and overall impression of the robots differently depending on their nationalities. The human-like robot was considered to be more robot-like than the product-like robot whereas there was no difference between the robots in both cultures on purchase intention. Implications for the robot design between Korea and Japan are discussed.
{"title":"How People Perceive Human- and Product-like Robots: Cross-cultural Analysis Between Japan and Korea","authors":"Hyewon Lee, Hyemee Kang, Sonya S. Kwak, Jaeryoung Lee, Min-Gyu Kim, Jun-Beom Kwon","doi":"10.1145/2814940.2815007","DOIUrl":"https://doi.org/10.1145/2814940.2815007","url":null,"abstract":"In this article, we present two robot design types: human-like and product-like robot. A human-like robot is designed to be similar to humans in the appearance or behavior. A product-like robot is designed to maximize the functionality of a product. As well as the comparison between the human-like robot and product-like robot, cultural differences between Korea and Japan on perceived intellectual capability, robot-likeness, usefulness, overall impression and purchase intention were investigated. People evaluated the intellectual capability, usefulness and overall impression of the robots differently depending on their nationalities. The human-like robot was considered to be more robot-like than the product-like robot whereas there was no difference between the robots in both cultures on purchase intention. Implications for the robot design between Korea and Japan are discussed.","PeriodicalId":427567,"journal":{"name":"Proceedings of the 3rd International Conference on Human-Agent Interaction","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127446910","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}
This paper introduces a voice emotion recognition framework to operate on mobile devices. The fundamental framework consists of detection of human voice, extraction of emotional features, and identification of an emotional state. We implemented a simple smartphone interface to verify the performance of the voice emotion recognition system operating on mobile device.
{"title":"Implementation of Voice Emotion Recognition for Interaction with Mobile Agent","authors":"Jeong-Sik Park, Gil-Jin Jang","doi":"10.1145/2814940.2815004","DOIUrl":"https://doi.org/10.1145/2814940.2815004","url":null,"abstract":"This paper introduces a voice emotion recognition framework to operate on mobile devices. The fundamental framework consists of detection of human voice, extraction of emotional features, and identification of an emotional state. We implemented a simple smartphone interface to verify the performance of the voice emotion recognition system operating on mobile device.","PeriodicalId":427567,"journal":{"name":"Proceedings of the 3rd International Conference on Human-Agent Interaction","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134448781","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}
A reasonable growth has been noticed in the Web of Things (WoT), in which different embedded devices are inter-connected with each other. These devices are capable of sharing and communicating over the web based application. On the other hand, integration of such devices (capillaries) need a comprehensive architecture, which is still missing. Therefore, this paper proposes the concept of Smart Society; propelling the notion of smart home. In the proposed smart society, we present an architecture for smart society. The proposed smart society consists of three domains, i.e., smart home and smart community, with supportive techniques and related challenges, and visualize of value added smart community. We then describe how to realize a robust networking among individual society. The feasibility and efficiency of the proposed system are implemented on Hadoop single node setup by testing the sample medical, sensory data sets and fire detection datasets. Finally, the results show that the proposed system architecture efficiently process, analyze, and integrates different datasets efficiently and triggers actions to provide safety measurements for elderly age people in smart home, vehicles in smart transportation system, and others.
{"title":"Integration of Capillary Devices in the Smart Society based on Web of Things","authors":"Awais Ahmad, M. Rathore, Anand Paul","doi":"10.1145/2814940.2814994","DOIUrl":"https://doi.org/10.1145/2814940.2814994","url":null,"abstract":"A reasonable growth has been noticed in the Web of Things (WoT), in which different embedded devices are inter-connected with each other. These devices are capable of sharing and communicating over the web based application. On the other hand, integration of such devices (capillaries) need a comprehensive architecture, which is still missing. Therefore, this paper proposes the concept of Smart Society; propelling the notion of smart home. In the proposed smart society, we present an architecture for smart society. The proposed smart society consists of three domains, i.e., smart home and smart community, with supportive techniques and related challenges, and visualize of value added smart community. We then describe how to realize a robust networking among individual society. The feasibility and efficiency of the proposed system are implemented on Hadoop single node setup by testing the sample medical, sensory data sets and fire detection datasets. Finally, the results show that the proposed system architecture efficiently process, analyze, and integrates different datasets efficiently and triggers actions to provide safety measurements for elderly age people in smart home, vehicles in smart transportation system, and others.","PeriodicalId":427567,"journal":{"name":"Proceedings of the 3rd International Conference on Human-Agent Interaction","volume":"126 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132716252","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}
Studies in collaborative learning show that learners with fewer social interaction skills have difficulty during collaborative activities with others. The present study investigates how such a learner's skills influence the performance of an online concept-learning tutoring task with a Pedagogical Conversational Agent (PCA). During the task, the learners were guided by a PCA that helped them formulate their explanations of a key concept taught in a large-scale class. The study assesses the degree of learner's social skills based on the autism spectrum quotient (AQ) and investigates how this level skills influences learning with the PCA. Results show that learners with higher social skills performed better on explanation activities with the PCA. This shows that social cognitive skills influence learning performance during communication-based learning support systems. The results of this study suggest that there is a need to design efficient online tutoring systems that consider a learner's social skills.
{"title":"Influence of Social Communication Skills on Collaborative Learning with a Pedagogical Agent: Investigation Based on the Autism-spectrum Quotient","authors":"Yugo Hayashi","doi":"10.1145/2814940.2814946","DOIUrl":"https://doi.org/10.1145/2814940.2814946","url":null,"abstract":"Studies in collaborative learning show that learners with fewer social interaction skills have difficulty during collaborative activities with others. The present study investigates how such a learner's skills influence the performance of an online concept-learning tutoring task with a Pedagogical Conversational Agent (PCA). During the task, the learners were guided by a PCA that helped them formulate their explanations of a key concept taught in a large-scale class. The study assesses the degree of learner's social skills based on the autism spectrum quotient (AQ) and investigates how this level skills influences learning with the PCA. Results show that learners with higher social skills performed better on explanation activities with the PCA. This shows that social cognitive skills influence learning performance during communication-based learning support systems. The results of this study suggest that there is a need to design efficient online tutoring systems that consider a learner's social skills.","PeriodicalId":427567,"journal":{"name":"Proceedings of the 3rd International Conference on Human-Agent Interaction","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130960960","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}
Midori Sugaya, Hirotaka Osawa, Yoshiko Okada, I. Giannopulu
Children suffering with learning and developmental disorders require daily training to develop their social skills. However, such daily training is sometimes not provided because it requires interactive help from therapists, and lots of special programs required for the training. We proposed an immersive digital dollhouse that enhances traditional psychological play therapy with sensors installed, while provides feedback from the sensors to the computer graphics (CG). The immersive digital dollhouse provides an immersive space for children, which develops their communication skills through their imaginary play with the complement of CG for enhancing the understanding of their situation, and it is easy to use in their home as daily training. We conducted an experiment with a 6-year old child with a similar level as the older children with developmental disorders. We found that the number of reactions was twice as many as with a normal dollhouse, and the number of miscommunications was less than one-tenth.
{"title":"Feel as Agent: Immersive Digital Dollhouse Enhances Sociality of Children with Developmental Disorders","authors":"Midori Sugaya, Hirotaka Osawa, Yoshiko Okada, I. Giannopulu","doi":"10.1145/2814940.2814963","DOIUrl":"https://doi.org/10.1145/2814940.2814963","url":null,"abstract":"Children suffering with learning and developmental disorders require daily training to develop their social skills. However, such daily training is sometimes not provided because it requires interactive help from therapists, and lots of special programs required for the training. We proposed an immersive digital dollhouse that enhances traditional psychological play therapy with sensors installed, while provides feedback from the sensors to the computer graphics (CG). The immersive digital dollhouse provides an immersive space for children, which develops their communication skills through their imaginary play with the complement of CG for enhancing the understanding of their situation, and it is easy to use in their home as daily training. We conducted an experiment with a 6-year old child with a similar level as the older children with developmental disorders. We found that the number of reactions was twice as many as with a normal dollhouse, and the number of miscommunications was less than one-tenth.","PeriodicalId":427567,"journal":{"name":"Proceedings of the 3rd International Conference on Human-Agent Interaction","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128739117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In order to make machines able to recognize various patterns, it is important to define an appropriate function for measuring similarities between different objects. Conventional similarity measures are devised mainly for 1D vector data, which may lead to loss of information of 2D matrix data. We cast the calculation of similarity between two matrices as a neural network problem, and design the architecture for learning a similarity measure. We provide experiments on real 2D matrix data in the face recognition and gesture recognition, where we show that the learning of a similarity measure leads to improvements in the performance of the recognition problem. Also we compare the performance of the proposed measure with conventional distance measures for 2D matrix data.
{"title":"Measuring Similarity Between Matrix Objects for Pattern Recognition","authors":"Hyunsoek Choi, Hyeyoung Park","doi":"10.1145/2814940.2814967","DOIUrl":"https://doi.org/10.1145/2814940.2814967","url":null,"abstract":"In order to make machines able to recognize various patterns, it is important to define an appropriate function for measuring similarities between different objects. Conventional similarity measures are devised mainly for 1D vector data, which may lead to loss of information of 2D matrix data. We cast the calculation of similarity between two matrices as a neural network problem, and design the architecture for learning a similarity measure. We provide experiments on real 2D matrix data in the face recognition and gesture recognition, where we show that the learning of a similarity measure leads to improvements in the performance of the recognition problem. Also we compare the performance of the proposed measure with conventional distance measures for 2D matrix data.","PeriodicalId":427567,"journal":{"name":"Proceedings of the 3rd International Conference on Human-Agent Interaction","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116827251","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}
Chaehyun Baek, Jung-Ju Choi, Jeonghye Han, Sonya S. Kwak
In this paper, a STEAM education was developed by applying intelligent product design. One promising approach to improve children's STEAM attitudes, knowledge, and skills is to utilize robotics in the program. As an intelligent product is a robot with the shape of the common object, intelligent product design could allow children to learn robotics and product design. Field trial of STEAM education was held at a Korean elementary school for two weeks. After the field trial, children evaluated the perception toward a common product and a developed intelligent product. The results showed that the intelligent product was perceived more positively and intelligent than the common product.
{"title":"Application of Intelligent Product Design on STEAM Education","authors":"Chaehyun Baek, Jung-Ju Choi, Jeonghye Han, Sonya S. Kwak","doi":"10.1145/2814940.2814988","DOIUrl":"https://doi.org/10.1145/2814940.2814988","url":null,"abstract":"In this paper, a STEAM education was developed by applying intelligent product design. One promising approach to improve children's STEAM attitudes, knowledge, and skills is to utilize robotics in the program. As an intelligent product is a robot with the shape of the common object, intelligent product design could allow children to learn robotics and product design. Field trial of STEAM education was held at a Korean elementary school for two weeks. After the field trial, children evaluated the perception toward a common product and a developed intelligent product. The results showed that the intelligent product was perceived more positively and intelligent than the common product.","PeriodicalId":427567,"journal":{"name":"Proceedings of the 3rd International Conference on Human-Agent Interaction","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129107563","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}
Reinforcement learning is one of research fields in artificial intelligence. The learning method usually assumes a discrete state in computer simulations. However, we must treat a continuous value in a realistic situation. In this paper, we investigate various techniques of the tile cording scheme which is a representative technique to handle continuous states. We check the performance of single tiling, multiple tiling, time-shift method and the proposed method in the issue of space search.
{"title":"Performance Evaluation of Tile Coding in Reinforcement Learning","authors":"Kenji Ota, T. Ozeki","doi":"10.1145/2814940.2814975","DOIUrl":"https://doi.org/10.1145/2814940.2814975","url":null,"abstract":"Reinforcement learning is one of research fields in artificial intelligence. The learning method usually assumes a discrete state in computer simulations. However, we must treat a continuous value in a realistic situation. In this paper, we investigate various techniques of the tile cording scheme which is a representative technique to handle continuous states. We check the performance of single tiling, multiple tiling, time-shift method and the proposed method in the issue of space search.","PeriodicalId":427567,"journal":{"name":"Proceedings of the 3rd International Conference on Human-Agent Interaction","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133382965","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}
Gwenaelle Cunha Sergio, R. Mallipeddi, Jun-Su Kang, Minho Lee
Images can convey emotion just like music. If that's so, then it might be possible that, given an image, one can obtain a music that can produce a similar reaction from the listener/viewer. The challenge lies in how to do that. In this paper, we analyze the image using the HSV color space model and assume that each one of the three components have a relation with basic music elements, like tone, pitch, rhythm and loudness. The image is then scanned from left to right and top to bottom in order to generate a sequence of notes. In the end, the emotional Mean Opinion Score (MOS) is used to evaluate the performance of the proposed method. This work could prove to be a very important contribution to the field of HCI because it can improve the interaction between computers and humans who are visually and/or hearing impaired. In the current work, we only consider two emotions; positive and negative.
{"title":"Generating Music from an Image","authors":"Gwenaelle Cunha Sergio, R. Mallipeddi, Jun-Su Kang, Minho Lee","doi":"10.1145/2814940.2814978","DOIUrl":"https://doi.org/10.1145/2814940.2814978","url":null,"abstract":"Images can convey emotion just like music. If that's so, then it might be possible that, given an image, one can obtain a music that can produce a similar reaction from the listener/viewer. The challenge lies in how to do that. In this paper, we analyze the image using the HSV color space model and assume that each one of the three components have a relation with basic music elements, like tone, pitch, rhythm and loudness. The image is then scanned from left to right and top to bottom in order to generate a sequence of notes. In the end, the emotional Mean Opinion Score (MOS) is used to evaluate the performance of the proposed method. This work could prove to be a very important contribution to the field of HCI because it can improve the interaction between computers and humans who are visually and/or hearing impaired. In the current work, we only consider two emotions; positive and negative.","PeriodicalId":427567,"journal":{"name":"Proceedings of the 3rd International Conference on Human-Agent Interaction","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130422485","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：