We present a driving route prediction method that is based on Hidden Markov Model (HMM). This method can accurately predict a vehicle’s entire route as early in a trip’s lifetime as possible without inputting origins and destinations beforehand. Firstly, we propose the route recommendation system architecture, where route predictions play important role in the system. Secondly, we define a road network model, normalize each of driving routes in the rectangular coordinate system, and build the HMM to make preparation for route predictions using a method of training set extension based onK-means++ and the add-one (Laplace) smoothing technique. Thirdly, we present the route prediction algorithm. Finally, the experimental results of the effectiveness of the route predictions that is based on HMM are shown.
Abstract-Radio Frequency Identification (RFID) technology is widely used to achieve indoor object tracking and positioning. Currently, many methods need to deploy a large number of reference tags beforehand and some are limited by antennas' spacing. Further, the signal propagation along Non-Line of Sight introduces multipath effects which will challenge the accuracy of RFID localization system. In this work, we propose a method based on measured phase to track mobile RFID tags with millimeter level (mm-level) accuracy. We first partition the surveillance region into square grids at mm-level and suppose that there is a virtual tag as the same as the tracked one in each grid. On this basis, for the case where the tags move along a known track with constant speed, we only need to locate the tag's initial position. We leverage phase periodicity to obtain some candidates and then eliminate position ambiguity by double difference true phase. And for the case where the tag's moving track is unknown to the system, we adopt a first-order Taylor series expansion to calculate the relative displacements of the tracked tag and then locate the initial position as the same process as tracking the known trajectory. In our experiment, our solution can achieve a mean error distance of 0.26cm and 0.55cm for known and unknown movement tracks respectively.
A method of vehicle route prediction based on social network analysis is proposed in this paper. The difference from proposed work is that, according to our collected vehicles’ past trips, we build a relationship model between different road segments rather than find the driving regularity of vehicles to predict upcoming routes. In this paper, firstly we depend on graph theory to build an initial road network model and modify related model parameters based on the collected data set. Then we transform the model into a matrix. Secondly, two concepts from social network analysis are introduced to describe the meaning of the matrix and we process it by current software of social network analysis. Thirdly, we design the algorithm of vehicle route prediction based on the above processing results. Finally, we use the leave-one-out approach to verify the efficiency of our algorithm.
A see-through-wall system can be used in life detection, military fields, elderly people surveillance. and gaming. The existing systems are mainly based on military devices, customized signals or pre-deployed sensors inside the room, which are very expensive and inaccessible for general use. Recently, a low-cost RFID technology has gained a lot of attention in this field. Since phase estimates of a battery-free RFID tag collected by a commercial off-the-shelf (COTS) RFID reader are sensitive to external interference, the RFID tag could be regarded as a battery-free sensor that detects reflections off targeted objects. The existing RFID-based system, however, needs to first learn the environment of the empty room beforehand to separate reflections off the tracked target. Besides, it can only track low-speed metal objects with high-positioning accuracy. Since the human body with its complex surface has a weaker ability to reflect radio frequency (RF) signals than metal objects, a battery-free RFID tag can capture only a subset of the reflections off the human body. To address these challenges, a RFID-based human motion sensing technology, called RF-HMS, is presented to track device-free human motion through walls. At first, we construct transfer functions of multipath channel based on phase and RSSI measurements to eliminate device noise and reflections off static objects like walls and furniture without learning the environment of the empty room before. Then a tag planar array is grouped by many battery-free RFID tags to improve the sensing performance. RF-HMS combines reflections from each RFID tag into a reinforced result. On this basis, we extract phase shifts to detect the absence or presence of any moving persons and further derive the reflections off a single moving person to identify his/her forward or backward motion direction. The results show that RF-HMS can effectively detect the absence or presence of moving persons with 100% accuracy and keep a high accuracy of more than 90% to track human motion directions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.