University of Electronic Science and Technology of China

About: University of Electronic Science and Technology of China is a education organization based out in Chengdu, China. It is known for research contribution in the topics: Computer science & Antenna (radio). The organization has 50594 authors who have published 58502 publications receiving 711188 citations. The organization is also known as: UESTC.

Towards enhancing the last-mile delivery: An effective crowd-tasking model with scalable solutions

Abstract: In urban logistics, the last-mile delivery from the warehouse to the consumer’s home has become more and more challenging with the continuous growth of E-commerce. It requires elaborate planning and scheduling to minimize the global traveling cost, but often results in unattended delivery as most consumers are away from home. In this paper, we propose an effective large-scale mobile crowd-tasking model in which a large pool of citizen workers are used to perform the last-mile delivery. To efficiently solve the model, we formulate it as a network min-cost flow problem and propose various pruning techniques that can dramatically reduce the network size. Comprehensive experiments were conducted with Singapore and Beijing datasets. The results show that our solution can support real-time delivery optimization in the large-scale mobile crowd-sourcing problem.

A New Deep-Q-Learning-Based Transmission Scheduling Mechanism for the Cognitive Internet of Things

Abstract: Cognitive networks (CNs) are one of the key enablers for the Internet of Things (IoT), where CNs will play an important role in the future Internet in several application scenarios, such as healthcare, agriculture, environment monitoring, and smart metering. However, the current low packet transmission efficiency of IoT faces a problem of the crowded spectrum for the rapidly increasing popularities of various wireless applications. Hence, the IoT that uses the advantages of cognitive technology, namely the cognitive radio-based IoT (CIoT), is a promising solution for IoT applications. A major challenge in CIoT is the packet transmission efficiency using CNs. Therefore, a new Q-learning-based transmission scheduling mechanism using deep learning for the CIoT is proposed to solve the problem of how to achieve the appropriate strategy to transmit packets of different buffers through multiple channels to maximize the system throughput. A Markov decision process-based model is formulated to describe the state transformation of the system. A relay is used to transmit packets to the sink for the other nodes. To maximize the system utility in different system states, the reinforcement learning method, i.e., the Q learning algorithm, is introduced to help the relay to find the optimal strategy. In addition, the stacked auto-encoders deep learning model is used to establish the mapping between the state and the action to accelerate the solution of the problem. Finally, the experimental results demonstrate that the new action selection method can converge after a certain number of iterations. Compared with other algorithms, the proposed method can better transmit packets with less power consumption and packet loss.

Micro optical sensors based on avalanching silicon light-emitting devices monolithically integrated on chips

Abstract: Silicon avalanche light-emitting devices (Si Av LEDs) offer various possibilities for realizing micro- and even nano- optical biosensors directly on chip. The light-emitting devices (LEDs) operate in the wavelength range of about 450-850nm, and their optical power emitted is of the order of a few hundreds of nW/µm2. These LEDs could be fabricated in micro- and nano- dimensions by using modern semiconductor fabrication processing technologies through the mainstream of silicon material. Through a series of experiments, the dispersion phenomena in the Si Av LED are observed. Also, its light emission point was proved to locate at about one micron just below the silicon-silicon oxide interface. Subsequently, a micro-fluidic channel sensor was designed by using the dispersion characteristics owned by the Si Av LED. The analytes flowing through a micro-fluidic channel could be studied by their specific transmittance and absorption spectra. Moreover, simulations verify that a novel designed waveguide-based sensor could be fabricated on chip between the Si optical source and the Si P-I-N detector.