Beijing University of Posts and Telecommunications

About: Beijing University of Posts and Telecommunications is a education organization based out in Beijing, Beijing, China. It is known for research contribution in the topics: MIMO & Quality of service. The organization has 39576 authors who have published 41525 publications receiving 403759 citations. The organization is also known as: BUPT.

Coverage-Enhancing Algorithm for Directional Sensor Networks

Abstract: Adequate coverage is very important for sensor networks to fulfill the issued sensing tasks. In traditional sensor networks, the sensors are based on omni-sensing model. However, directional sensing sensors are with great application chances, typically in video sensor networks. Toward this end, this paper addresses the problem of enhancing coverage in a directional sensor network. First, based on a rotatable directional sensing model, we present a method to deterministically estimate the amount of directional nodes for a given coverage rate. We also employ Sensing Connected Sub-graph (SCSG) to divide a directional sensor network into several parts in a distributed manner, in order to decrease time complexity. Moreover, the concept of convex hull is introduced to model each sensing connected sub-graph. According to the characteristic of adjustable sensing directions of directional nodes, we study a coverage-enhancing algorithm to minimize the overlapping sensing area of directional sensors only with local topology information. Extensive simulation is conducted to verify the effectiveness of our solution and we give detailed discussions on the effects of different system parameters.

Facilitating Robust 60 GHz Network Deployment By Sensing Ambient Reflectors

Abstract: 60 GHz millimeter-wave networks represent the next frontier in high-speed wireless access technologies. Due to the use of highly directional and electronically steerable beams, the performance of 60 GHz networks becomes a sensitive function of environment structure and reflectivity, which cannot be handled by existing networking paradigms. In this paper, we propose E-Mi, a framework that harnesses 60 GHz radios’ sensing capabilities to boost network performance. E-Mi uses a single pair of 60 GHz transmitter and receiver to sense the environment. It can resolve all dominant reflection paths between the two nodes, from which it reconstructs a coarse outline of major reflectors in the environment. It then feeds the reflector information into a ray-tracer to predict the channel and network performance of arbitrarily located links. Our experiments on a custom-built 60 GHz testbed verify that E-Mi can accurately sense a given environment, and predict the channel quality of different links with 2.8 dB median error. The prediction is then used to optimize the deployment of 60 GHz access points, with 2.2× to 4.5× capacity gain over empirical approaches.

Deep Reinforcement Learning Based Dynamic Channel Allocation Algorithm in Multibeam Satellite Systems

Abstract: Dynamic channel allocation (DCA) is the key technology to efficiently utilize the spectrum resources and decrease the co-channel interference for multibeam satellite systems. Most works allocate the channel on the basis of the beam traffic load or the user terminal distribution of the current moment. These greedy-like algorithms neglect the intrinsic temporal correlation among the sequential channel allocation decisions, resulting in the spectrum resources underutilization. To solve this problem, a novel deep reinforcement learning (DRL)-based DCA (DRL-DCA) algorithm is proposed. Specifically, the DCA optimization problem, which aims at minimizing the service blocking probability, is formulated in the multibeam satellite systems. Due to the temporal correlation property, the DCA optimization problem is modeled as the Markov decision process (MDP) which is the dominant analytical approach in DRL. In modeled MDP, the system state is reformulated into an image-like fashion, and then, convolutional neural network is used to extract useful features. Simulation results show that the DRL-DCA algorithm can decrease the blocking probability and improve the carried traffic and spectrum efficiency compared with other channel allocation algorithms.

A Multiscale Fusion Convolutional Neural Network for Plant Leaf Recognition

Abstract: Plant leaf recognition is a computer vision task used to automatically recognize plant species. It is very challenging since rich plant leaf morphological variations, such as sizes, textures, shapes, venation, and so on. Most existing plant leaf methods typically normalize all plant leaf images to the same size and recognize them at one scale, resulting in unsatisfactory performances. In this letter, a multiscale fusion convolutional neural network (MSF-CNN) is proposed for plant leaf recognition at multiple scales. First, an input image is down-sampled into multiples low resolution images with a list of bilinear interpolation operations. Then, these input images with different scales are step-by-step fed into the MSF-CNN architecture to learn discriminative features at different depths. At this stage, the feature fusion between two different scales is realized by a concatenation operation, which concatenates feature maps learned on different scale images from a channel view. Along with the depth of the MSF-CNN, multiscale images are progressively handled and the corresponding features are fused. Third, the last layer of the MSF-CNN aggregates all discriminative information to obtain the final feature for predicting the plant species of the input image. Experiments show the proposed MSF-CNN method is superior to multiple state-of-the art plant leaf recognition methods on the MalayaKew Leaf dataset and the LeafSnap Plant Leaf dataset.