Information and communication technologies (ICTs) have a profound impact on the current state and envisioned future of automobiles. This paper presents an overview of research on ICT-based support and assistance services for the safety of future connected vehicles. A general classification and a brief description of the focus areas for research and development in this direction are given under the titles of vehicle detection, road detection, lane detection, pedestrian detection, drowsiness detection, and collision avoidance. Following an overview and taxonomy of the reviewed research articles, a categorized literature survey of safety critical applications is presented in detail. Future research directions are also highlighted.
Wireless access technologies such as UMTS with HSPA extensions, WiMAX, and Flash-OFDM and the convergence towards next generation heterogeneous networks enable the realization of always best connected scenarios. As the resulting heterogeneous networks become easier to access and more reliable to depend on, novel telemedicine services such as vehicular emergency applications emerge. Due to their life-critical characteristics, these applications require connectivity throughout the heterogeneous network. In this study, we propose MIPGATE, our mobile connectivity gateway for vehicular applications in next generation heterogeneous networks. MIPGATE contains modules for the access technologies currently available and a decision mechanism to switch intelligently to the connection offering the most suitable conditions. Link layer triggers and additional context information are used to optimize the handover decision process. MIPGATE is deployed within StrokeNet, a mobile telemedicine project for the remote diagnosis of stroke patients using real-time audio and videoconferencing. The MIPGATE system is validated through measurements on throughput, delay, packet loss, and handover latencies using public wireless network infrastructures with the UMTS technology and a Beyond-3G testbed featuring a Flash-OFDM test network. For the payload packets, mean handover times of 118 ms in case of handovers to UMTS/HSDPA and 23 ms in case of handovers to Flash-OFDM have been achieved in a real-world network setup. The overall packet loss rate is 0.21% and equally distributed over the duration of the measurements. The results show that MIPGATE supports network connectivity under mobility as required by novel vehicular telemedicine applications and demanding real-time services.
article Share on Agent-oriented technology for telecommunications: introduction Editor: Sahin Albayrak Technical Univ. of Berlin, Berlin Technical Univ. of Berlin, BerlinView Profile Authors Info & Claims Communications of the ACMVolume 44Issue 4April 2001 pp 30–33https://doi.org/10.1145/367211.367240Published:01 April 2001Publication History 6citation952DownloadsMetricsTotal Citations6Total Downloads952Last 12 Months23Last 6 weeks1 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my Alerts New Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access
A limitation for collaborative robots (cobots) is their lack of ability to adapt to human partners, who typically exhibit an immense diversity of behaviors. We present an autonomous framework as a cobot's real-time decision-making mechanism to anticipate a variety of human characteristics and behaviors, including human errors, toward a personalized collaboration. Our framework handles such behaviors in two levels: 1) short-term human behaviors are adapted through our novel Anticipatory Partially Observable Markov Decision Process (A-POMDP) models, covering a human's changing intent (motivation), availability, and capability; 2) long-term changing human characteristics are adapted by our novel Adaptive Bayesian Policy Selection (ABPS) mechanism that selects a short-term decision model, e.g., an A-POMDP, according to an estimate of a human's workplace characteristics, such as her expertise and collaboration preferences. To design and evaluate our framework over a diversity of human behaviors, we propose a pipeline where we first train and rigorously test the framework in simulation over novel human models. Then, we deploy and evaluate it on our novel physical experiment setup that induces cognitive load on humans to observe their dynamic behaviors, including their mistakes, and their changing characteristics such as their expertise. We conduct user studies and show that our framework effectively collaborates non-stop for hours and adapts to various changing human behaviors and characteristics in real-time. That increases the efficiency and naturalness of the collaboration with a higher perceived collaboration, positive teammate traits, and human trust. We believe that such an extended human adaptation is key to the long-term use of cobots.
In this paper we introduce the Smart Tempo-Spatial Hotspots Finder (Smart-TSH-Finder) for smart data crawling in the Second Life (SL) virtual world. Classical methods of crawling data from SL lead to irrelevant data content because of the dynamic nature of avatars and objects in SL. In order to build artificially intelligent expert avatar agents that are able to provide intelligent services for other typical avatars in virtual world we attempt to enhance the quality of extracted data from SL. Based on experimental observation, avatars tend to gather in some places for different amounts of time, which forms temporal and spatial hotspots. Utilizing the Tempo-Spatial characteristics of the avatars behavior in virtual worlds could improve the quality of the extracted data. Smart-TSHFinder implements a Tempo-Spatial Hotspots finding mechanism to crawl dynamic contents such as chat conversations from Second Life. The system introduces two mechanisms: the Tempo-Spatial Hotspots Detection, and the Tempo-Spatial Hotspots Prediction. Our smart chat conversations that have been crawled showed good enhancement in content quality of the crawled chat conversation which will enrich the future textual analysis work. Additionally, we found that extracting avatars interactions and behavior in the Tempo-Spatial Hotspots in addition to chat conversations can help in generation a more coherent social network model for SL.
This work presents the vision for the development of virtual home health station to monitor well-being of people in a long term sense. We aim to provide a concept for the integrated health solution with possible research directions to constantly monitor patient's current health condition, emotional and environmental state with ensuring the continuity of care and to provide immediate guidance in case of significant changes on their health conditions. This system will empower people to take a more active role in the management of their own personal health for the better health conditions.
Context-awareness for information retrieval is a challenging problem as information about the user's current situation is rarely available. However, if such information is available, retrieval and recommendation systems could use it to find information more relevant to their users' current context. We present a model for creating contextualized recommendations based on implicitly expressed context via keywords assigned to previously seen items and other available information. When employed, the model can create ad hoc recommendation with improved accuracy.
Recommender systems assist users in finding relevant entities according to their individual preferences. The entities' properties along with their relationships must be considered in order to articulate good recommendations. In this paper, we present an approach for developing an adaptive hybrid recommender system with semantic data. Such data is represented as large graph of nodes (semantic entities) and edges (semantic relations) filled with contents collected from Linked-Open-Data sources. The system implements different algorithms to generate recommendations supporting users in finding relevant, but potentially unknown movies. The system provides users with explicit explanations helping them to understand why a movie is relevant. Users may refine requests according to their individual preferences. The system considers run-time complexity to guarantee a short request response time for individually adapted requests.
