The proceedings contain 74 papers. The topics discussed include: multi-modal adversarial training for crisis-related data classification on social media; learning mobility flows from urban features with spatial intera...
ISBN:
(纸本)9781728169972
The proceedings contain 74 papers. The topics discussed include: multi-modal adversarial training for crisis-related data classification on social media; learning mobility flows from urban features with spatial interaction models and neural networks; LAXARY: a trustworthy explainable twitter analysis model for post-traumatic stress disorder assessment; from smart city to smart citizen: rewarding waste recycle by designing a data-centric IoT based garbage collection service; MobIntel: sensing and analytics infrastructure for urban mobility intelligence; data ingestion and inspection for smart city applications; a scalable distributed system for precision irrigation; towards AI conversing : FloodBot using deep learning model stacks; and privacy-aware sensor data upload management for securely receiving smart home service.
This paper introduces the normalized unused sensing capacity to measure the amount of information that a sensor is currently gathering relative to its theoretical maximum. This quantity can be computed using entirely ...
详细信息
This paper introduces the normalized unused sensing capacity to measure the amount of information that a sensor is currently gathering relative to its theoretical maximum. This quantity can be computed using entirely local information and works for arbitrary sensor models, unlike previous literature on the subject. This is then used to develop a distributed coverage control strategy for a team of heterogeneous sensors that automatically balances the load based on the current unused capacity of each team member. This algorithm is validated in a multi-target tracking scenario, yielding superior results to standard approaches that do not account for heterogeneity or current usage rates.
This article represents the view of the authors about the needs and the implementation of a distributed system, among all institutes in Bulgaria, for management of plant genetics resources, according the standards def...
详细信息
Recently, Stochastic computing has sparked interest in Bayesian inference resolution for its promising efficiency in area and power consumption. This representation encodes values by the rate of bits at ‘1’ in a bit...
详细信息
Recently, Stochastic computing has sparked interest in Bayesian inference resolution for its promising efficiency in area and power consumption. This representation encodes values by the rate of bits at ‘1’ in a bit-stream. Still, in a sequential architecture, most of the energy cost is due to the long computation time required for achieving a satisfying accuracy. In this paper, we propose a multi-rail architecture for Bayesian sensor fusion problems based on a Shift Register Isolator and permutations in order to reduce the computation time and thus, the energy consumption, without a significant increase in area. Indeed, with this resource sharing strategy, we are able to reduce the energy consumption by up to 73% in return for an area overhead of 24%, while maintaining the computation accuracy.
The automatic design of robot teams and environments for construction tasks is an important research problem. Though most work to date has focused on visual sensing robots, it would be of great interest to know algori...
The automatic design of robot teams and environments for construction tasks is an important research problem. Though most work to date has focused on visual sensing robots, it would be of great interest to know algorithmic options for design relative to robots that sense scalar fields such as chemical gradients. In this paper we give the first computational and parameterized complexity analyses of the problems of designing scalar-field sensing robot teams and environments for construction tasks. Our results suggest that the pattern of tractability and intractability results for scalar-field sensing robots is broadly similar to that for visual sensing robots.
To cope with rapid increases in both the number of smart devices and the amount of computation-intensive edge applications on such devices, distributed cross-device edge computingsystems have received much attention ...
详细信息
While ubiquitous computing remains vastly applied in urban environments, their applications in ocean environment remain scarce due to the limitations in range and cost of current radio technology. This hinders environ...
详细信息
ISBN:
(数字)9781728147161
ISBN:
(纸本)9781728147161
While ubiquitous computing remains vastly applied in urban environments, their applications in ocean environment remain scarce due to the limitations in range and cost of current radio technology. This hinders environmental telemetry in the oceans and other remote areas. In this study, we explore the usage of IoT and Long Range Radio Communication (LoRa) in ocean environments. We study the maximum distance for LoRa and a potential location estimation based on the same technology using the passive RSSI analysis. Using three coastal based nodes and a node mounted on a sea vessel, we report a maximum range of 83.6km. We also achieve a location error within a radius of 3.4km (4% of maximum distance) in the sea. These results support marine biologist expeditions, allowing them to use low-cost, long-lasting and easy to deploy solutions for tracking marine objects and species in open ocean, providing them data in near-real-time. We discuss the findings from used models, outlining limitations, and providing a scenario for future ubiquitous IoT applications for tracking sea objects.
The wireless sensor network (WSN) has been gaining attraction in all fields. The range of sensors integrated into related applications is exploding. In fact, the future is moving towards the Internet of Things (IoT) a...
详细信息
ISBN:
(纸本)9781450377324
The wireless sensor network (WSN) has been gaining attraction in all fields. The range of sensors integrated into related applications is exploding. In fact, the future is moving towards the Internet of Things (IoT) and it is predicable to need deploying billions of sensors for monitoring. Such considerable amount of connected devices must offer efficient services for diverse applications. This vision directly depends on the efficiency of WSN protocols. In this way, our idea is to enhance the medium access scheme exploiting typical Medium Access Control (MAC) protocols. We propose a flexible hybrid MAC protocol that combines contention and scheduling aspects. It is designed to overcome traffic changes constraints, especially emergency cases. To achieve our goals, we join Career Sense Multiple Access / Collision Avoidance (CSMA/CA) and Time Division Multiple Access (TDMA) behaviors, and we adapt the channel access strategy according to traffic priorities. Such access scheme permits to guarantee transmitting urgent data efficiently.
This paper focuses on the development of the concept of an active wireless sensor network (WSN) as a basis for improving the checkability of high-risk facilities in post-accident monitoring. The use of a drone system ...
详细信息
ISBN:
(纸本)9781665426060
This paper focuses on the development of the concept of an active wireless sensor network (WSN) as a basis for improving the checkability of high-risk facilities in post-accident monitoring. The use of a drone system as WSN nodes provides a mobility network, the advantages of which are analyzed from the standpoint of improving the controllability and observability of the object in difficult post-accident conditions. The possibilities of renewing the resources of the mobile WSN, quick adaptation to the realities of training and reconfiguration as factors of ensuring high checkability of post-emergency objects are investigated. An analogy is drawn in the rating of checkability for digital circuits in critical systems and post-accident checkability of increased risk objects. The possibilities of active WSN, provided by its mobility, are analyzed.
Backward motion of articulated vehicles is a challenging task even for experienced drivers, since these systems are highly nonlinear and their movement is unstable. In this paper a review of the nonlinear path trackin...
详细信息
ISBN:
(纸本)9781728198095
Backward motion of articulated vehicles is a challenging task even for experienced drivers, since these systems are highly nonlinear and their movement is unstable. In this paper a review of the nonlinear path tracking control law based on exact linearization of a parameterized articulated vehicle composed of a car-like truck and N passive trailers is presented. Limitations of this path tracking procedure are discussed, particularly the automation of real world heavy goods articulated vehicles.
暂无评论