The Experts below are selected from a list of 303 Experts worldwide ranked by ideXlab platform
Heishiro Toyoda - One of the best experts on this subject based on the ideXlab platform.
-
Vehicle Automation–Other Road User Communication and Coordination: Theory and Mechanisms
IEEE Access, 2020Co-Authors: Joshua E. Domeyer, Heishiro ToyodaAbstract:When automobiles were first introduced in the early 1900s, poor Communication and unsafe interactions between drivers and other road Users generated resistance. This created a need for new infrastructure, vehicle design, and social norms to mitigate their negative effects on society. Vehicle automation may lead to similar challenges as drivers are supplanted by machines, potentially eliminating social behaviors that serve to smooth on-road Communication and coordination. Through a review of Communication, robotics, and traffic engineering literature, we explore the mechanisms that allow people to communicate on the road. We show the sensitivity of road Users to signals that are sent through vehicle motion, suggesting a need to design vehicle automation kinematics for Communication and not just external lighting signals. The framework further points to interdependence in Communication where road Users modulate their behaviors concurrently to exchange information and develop common ground. Designing automation to support common ground may smooth negotiations by generating interpretable signals in ambiguous situations. We propose a process to make automation observable and directable for other road Users by considering vehicle motion during development of algorithms, interfaces, and interactions. Road Users will be incidental Users of vehicle automation-Users whose goals are not directly supported by the technology-and poor Communication with them may undermine the safety and acceptance of vehicle automation. As the reach of automation grows, Communication among humans and machines may fundamentally change social interactions, requiring a framework to guide the process of making automation interactions smooth and natural.
Zhang Xiao - One of the best experts on this subject based on the ideXlab platform.
-
Study on Difference Spread Spectrum Multi-User Communication Based on Vector Sensor
Future Control and Automation, 2012Co-Authors: Yang Sen, Yin Jinwei, Zhang Xiao, Yu YunAbstract:In order to inhibit multi-path, low processing gain, frequency and phase error problem brought by fast phase changing, multi-path and complex characteristic of underwater channel, difference coherent modulation underwater Communication system, vector sensor as well as time reversal mirror is used in this paper. Vector sensor measures sound pressure and velocity information at the same point simultaneously which has dipole directivity and electrical rotation directivity. With vector combination directivity can be adjusted to enhance SNR and quality of Communication. Channel equilibrium and inhibition of multi-path interference can be achieved by time reversal mirror which is used for multi-User Communication who locates in different position with low channel relation. Simulation testifies the feasibility and reliability of the method mentioned in this paper.
-
Underwater Multi-User Communication Based on Distributed Time Reversal
Computer Simulation, 2009Co-Authors: Zhang XiaoAbstract:The application of time reversal technique in the underwater acoustic Communication can significantly reduce the intersymbol interference(ISI) caused by multi-path propagation,and increase the Communication data rate by using multi-path propagation feature in the ocean channel.However,a vertical linear array is required in the traditional time reversal Communication,which results in the complexion of multi-node Communication networks. This paper proposed a distributed time reversal Communication project by using the hardware resources of independent single node of the multi-node Communication networks instead of vertical linear array of traditional method. The simulation result reveals that this proposed distributed time reversal system could realize the focusing of multi -path signal,alleviating the ISI caused by multi-path propagation.Moreover,better system performance could be achieved by combining this technique with equalization.
Doree Dunca Seligma - One of the best experts on this subject based on the ideXlab platform.
-
connecting content to community in social media via image content User tags and User Communication
International Conference on Multimedia and Expo, 2009Co-Authors: Munmu De Choudhury, Hari Sundaram, Ajita Joh, Doree Dunca SeligmaAbstract:In this paper we develop a recommendation framework to connect image content with communities in online social media. The problem is important because Users are looking for useful feedback on their uploaded content, but finding the right community for feedback is challenging for the end User. Social media are characterized by both content and community. Hence, in our approach, we characterize images through three types of features: visual features, User generated text tags, and social interaction (User Communication history in the form of comments). A recommendation framework based on learning a latent space representation of the groups is developed to recommend the most likely groups for a given image. The model was tested on a large corpus of Flickr images comprising 15,689 images. Our method outperforms the baseline method, with a mean precision 0.62 and mean recall 0.69. Importantly, we show that fusing image content, text tags with social interaction features outperforms the case of only using image content or tags.
Doree Duncan Seligmann - One of the best experts on this subject based on the ideXlab platform.
-
ICME - Connecting content to community in social media via image content, User tags and User Communication
2009 IEEE International Conference on Multimedia and Expo, 2009Co-Authors: Munmun De Choudhury, Hari Sundaram, Yu-ru Lin, Ajita John, Doree Duncan SeligmannAbstract:In this paper we develop a recommendation framework to connect image content with communities in online social media. The problem is important because Users are looking for useful feedback on their uploaded content, but finding the right community for feedback is challenging for the end User. Social media are characterized by both content and community. Hence, in our approach, we characterize images through three types of features: visual features, User generated text tags, and social interaction (User Communication history in the form of comments). A recommendation framework based on learning a latent space representation of the groups is developed to recommend the most likely groups for a given image. The model was tested on a large corpus of Flickr images comprising 15,689 images. Our method outperforms the baseline method, with a mean precision 0.62 and mean recall 0.69. Importantly, we show that fusing image content, text tags with social interaction features outperforms the case of only using image content or tags.
Hari Sundaram - One of the best experts on this subject based on the ideXlab platform.
-
connecting content to community in social media via image content User tags and User Communication
International Conference on Multimedia and Expo, 2009Co-Authors: Munmu De Choudhury, Hari Sundaram, Ajita Joh, Doree Dunca SeligmaAbstract:In this paper we develop a recommendation framework to connect image content with communities in online social media. The problem is important because Users are looking for useful feedback on their uploaded content, but finding the right community for feedback is challenging for the end User. Social media are characterized by both content and community. Hence, in our approach, we characterize images through three types of features: visual features, User generated text tags, and social interaction (User Communication history in the form of comments). A recommendation framework based on learning a latent space representation of the groups is developed to recommend the most likely groups for a given image. The model was tested on a large corpus of Flickr images comprising 15,689 images. Our method outperforms the baseline method, with a mean precision 0.62 and mean recall 0.69. Importantly, we show that fusing image content, text tags with social interaction features outperforms the case of only using image content or tags.
-
ICME - Connecting content to community in social media via image content, User tags and User Communication
2009 IEEE International Conference on Multimedia and Expo, 2009Co-Authors: Munmun De Choudhury, Hari Sundaram, Yu-ru Lin, Ajita John, Doree Duncan SeligmannAbstract:In this paper we develop a recommendation framework to connect image content with communities in online social media. The problem is important because Users are looking for useful feedback on their uploaded content, but finding the right community for feedback is challenging for the end User. Social media are characterized by both content and community. Hence, in our approach, we characterize images through three types of features: visual features, User generated text tags, and social interaction (User Communication history in the form of comments). A recommendation framework based on learning a latent space representation of the groups is developed to recommend the most likely groups for a given image. The model was tested on a large corpus of Flickr images comprising 15,689 images. Our method outperforms the baseline method, with a mean precision 0.62 and mean recall 0.69. Importantly, we show that fusing image content, text tags with social interaction features outperforms the case of only using image content or tags.
