1 January 2012 in The Scientific World Journal
For greenhouse gas (GHG) emissions by Beijing economy 2007, a concrete emission inventory covering carbon dioxide (CO2), methane (CH4), and nitrous oxide (N2O) is presented and associated with an input-output analysis to reveal the local GHG embodiment in final demand and trade without regard to imported emissions. The total direct GHG emissions amount to 1.06E + 08 t CO2-eq, of which energy-related CO2emissions comprise 90.49%, non-energy-related CO2emissions 6.35%, CH4emissions 2.33%, and N2O emissions 0.83%, respectively. In terms of energy-related CO2emissions, the largest source is coal with a percentage of 53.08%, followed by coke with 10.75% and kerosene with 8.44%. Sector 26 (Construction Industry) holds the top local emissions embodied in final demand of 1.86E + 07 t CO2-eq due to its considerable capital, followed by energy-intensive Sectors 27 (Transport and Storage) and 14 (Smelting and Pressing of Ferrous and Nonferrous Metals). The GHG emissions embodied in Beijing's exports are 4.90E + 07 t CO2-eq, accounting for 46.01% of the total emissions embodied in final demand. The sound scientific database totally based on local emissions is an important basis to make effective environment and energy policies for local decision makers.
24 February 2020 in IEEE Transactions on Industrial Informatics
Speech is a natural user interface for the Internet of Things system. However, the presence of noise affects severely the performance of such system. With the deployment of smart devices with microphones, one can form a powerful acoustic sensor network to enhance the speech via beamforming techniques. On the other hand, reliability of data transmission also determines the beamforming performance, since faulty data will drift the beamformer steering location randomly. Currently, there is no protection scheme for acoustic data transmitted over the wireless network in order to keep steady beamforming performance. In this article, we design a compound distributed beamformer, where nodes are grouped and the system is embedded with blockchain technology to protect the data integrity during transmission. It attempts to provide more possible reliable connections between groups. Simulated experiments show that the distributed beamformer with blockchain protection is able to maintain steady beamforming performance.
2 May 2024 in Neural Computing and Applications
Deep neural networks (DNNs) have been applied in many pattern recognition or object detection applications. DNNs generally consist of millions or even billions of parameters. These demanding computational storage and requirements impede deployments of DNNs in resource-limited devices, such as mobile devices, micro-controllers. Simplification techniques such as pruning have commonly been used to slim DNN sizes. Pruning approaches generally quantify the importance of each component such as network weight. Weight values or weight gradients in training are commonly used as the importance metric. Small weights are pruned and large weights are kept. However, small weights are possible to be connected with significant weights which have impact to DNN outputs. DNN accuracy can be degraded significantly after the pruning process. This paper proposes a roulette wheel-like pruning algorithm, in order to simplify a trained DNN while keeping the DNN accuracy. The proposed algorithm generates a branch of pruned DNNs which are generated by a roulette wheel operator. Similar to the roulette wheel selection in genetic algorithms, small weights are more likely to be pruned but they can be kept; large weights are more likely to be kept but they can be pruned. The slimmest DNN with the best accuracy is selected from the branch. The performance of the proposed pruning algorithm is evaluated by two deterministic datasets and four non-deterministic datasets. Experimental results show that the proposed pruning algorithm generates simpler DNNs while DNN accuracy can be kept, compared to several existing pruning approaches.