Search

Alpha-N - A self-powered, wheel-driven Automated Delivery Robot (ADR) is presented in this paper. The ADR is capable of navigating autonomously by detecting and avoiding objects or obstacles in its path. It uses a vector map of the path and calculates the shortest path by Grid Count Method (GCM) of Dijkstra’s Algorithm. Landmark determination with Radio Frequency Identification (RFID) tags are placed in the path for identification and verification of source and destination, and also for the re-calibration of the current position. On the other hand, an Object Detection Module (ODM) is built by Faster R-CNN with VGGNet-16 architecture for supporting path planning by detecting and recognizing obstacles. The Path Planning System (PPS) is combined with the output of the GCM, the RFID Reading System (RRS) and also by the binary results of ODM. This PPS requires a minimum speed of 200 RPM and 75 s duration for the robot to successfully relocate its position by reading an RFID tag. In the result analysis phase, the ODM exhibits an accuracy of 83.75%, RRS shows 92.3% accuracy and the PPS maintains an accuracy of 85.3%. Stacking all these 3 modules, the ADR is built, tested and validated which shows significant improvement in terms of performance and usability comparing with other service robots.

Seventy percent of the population in Myanmar lives in rural areas. Although health workers are adequately trained, they are overburdened due to understaffing and insufficient supplies. Literature confirms that information and communication technologies can extend the reach of healthcare. In this paper, we present an SMS-based social network that aims to help health workers to interact with other medical professionals through topic-based message delivery. Topics describe interests of users and the content of message. A message is delivered by matching message content with user interests. Users describe topics as ICD- 10 codes, a comprehensive medical taxonomy. In this ICD-10 coded SMS, a set of prearranged codes provides a common language for users to send structured information that fits inside an SMS.

When people need help they often turn to their social peers for reliable information, recommendation or guidance. It is often difficult to find someone in the vicinity for help or communicate with someone from a distant place who can provide reliable help. Conveying the actual context of the question during remote communication is a cumbersome task, especially when avoiding speech communication. Our approach selects and prioritizes the contextual data for a question, based on the question content.We have developed a prototype for mobile users - the Ubiquitous Help System (UHS) - that implements a mixed-initiative approach for capturing, selecting and prioritizing contextual information as well as for selecting a group of users to send the question. UHS processes the user questions for clues on what context to include and presents its suggestions to the user. Contextual data that can be retrieved using the available sensors on the mobile device is automatically included for sending to the receiving parties alongside the question.

Efficient delivery of information in vehicular networks is crucial for the creation of useful and usable applications that need to cope with nomadic large-scale environments. Context-awareness is often key to improve efficiency of a vehicle network since it allows to make informed decisions on the data routing, data locality and data necessity for different moving objects. In this paper we show how the social network of vehicle residents, as part of the overall context, allows us to improve the information sharing in the vehicular network significantly. We demonstrate this by deploying a social ubiquitous-help-system (UHS) on top of a vehicular network. We analyze how UHS operates in a vehicular network using a network simulation of realistic large scale vehicular movement data and show that the social interactions increases the efficiency, relevance and quality of information in data delivery. ispartof: pages:1188-1194 ispartof: Proceedings of the 2010 ACM Symposium on Applied Computing pages:1188-1194 ispartof: SAC location:Sierre date:22 Mar - 26 Mar 2010 status: published

International audience; In Western society, the elderly represent a rapidly growing demographic group. For this group, dementia has become an important cause of dependencies on others and causes difficulties with independent living. Typical symptoms of the dementia syndrome are decreased location awareness and difficulties in situating ones activities in time, thus hindering long term plans and activities. We present our approach in creating an interactive system tailored for the needs of the early phases of the dementia syndrome. Given the increasing literacy with mobile technologies in this group, we propose an approach that exploits mobile technology in combination with the physical and social context to support prolonged independent living. Our system strengthens the involvement of caregivers through the patient's social network. We show that applications for people suffering from dementia can be created by explicitly taking into account context in the design process. Context dependencies that are defined in an early stage in the development process are propagated as part of the runtime behavior of the interactive system.

We present an approach to exploit social and spatio-temporal context in order to improve information dissemination in dynamic largescale public spaces. We illustrate it by applying a proposed measure of geo-social relevance of each individual in a simulated vehicular network and by comparing the performance of different network message passing techniques in an inter-vehicle ‘help-me-best-and-do-it-fast’ communication scenario. We conclude that the use of social networking capabilities of an individual combined with knowledge about their spatio-temporal context information significantly improves purposeful interaction between individuals in terms of both the efficiency of the network data dissemination and the quality of the delivered information. ispartof: pages:107-116 ispartof: LNCS vol:6439 issue:6439 pages:107-116 ispartof: First International Joint Conference on Ambient Intelligence (AmI'10) location:Malaga, Spain date:10 Nov - 12 Nov 2010 status: published

Human activity is highly influenced by the context and environment of the user. Presence of other users in the vicinity can also influence the context of use and thus activity. In ubiquitous computing environments, people are surrounded by numerous computing devices helping them to carry out various tasks. However, users seek precise and fine-grained information that is not provided by the computing environment but required to carry out their tasks. Especially nomadic users have little choice than to call upon help from other people present in their vicinity. There are social issues (e.g. availability and interruptibility) along with issues of relevance and reliability to find the most appropriate person to ask for information. Identifying this person is still a challenge today. We have developed software prototype U-Help-System (UHS) to demonstrate how using a social network in combination with the user profile and preferences, can help nomadic person to approximate in selecting people that can support the user in a large scale ubiquitous computing environment.

Recent work demonstrates the potential for extracting patterns from users' behavior as detected by sensors. Since there is currently no generalized framework for reasoning about activity-aware applications, designers can only rely on the existing systems for guidance. However, these systems often use a custom, domain-specific definition of activity pattern . Consequently the guidelines designers can extract from individual systems are limited to the specific application domains of those applications. In this paper, we introduce five high-level guidelines or commandments for designing activity-aware applications. By considering the issues we outlined in this paper, designers will be able to avoid common mistakes inherent in designing activity-aware applications.