Search

Currently, against the background of carbon trading policies, carbon dioxide is attributed commodity properties for market trading within carbon trading. Relevant data show that, in recent years, logistics enterprises have been facing continuously growing demand and carbon emissions have continuously increased; therefore, enterprises urgently need to strengthen their green transformation. Scientific and rational decision-making tools play a meaningful role in helping enterprises improve their competitiveness. In this context, a new three-way decision-making model based on attribute reduction and hesitation degree is proposed. First, an attribute reduction is performed. The attributes of three types of logistics enterprises are simplified according to the carbon emission evaluation attributes proposed in this study to determine their respective minimum attribute sets. Subsequently, the decision and loss function matrices are established considering the hesitation degree. The conditional probability is calculated using intuitionistic fuzzy similarity, and the probability threshold is calculated using the loss function matrix considering the hesitation degree. Finally, case studies and comparative analyses are conducted to illustrate the practicality and rationality of the proposed method. [ABSTRACT FROM AUTHOR]

Acceleration and compression on deep Convolutional Neural Networks (CNNs) have become a critical problem to develop intelligence on resource-constrained devices. Previous channel pruning can be easily deployed and accelerated without specialized hardware and software. However, weight-level redundancy is not well explored in channel pruning, which results in a relatively low compression ratio. In this work, we propose a Low-rank Approximated channel Pruning (LAP) framework to tackle this problem with two targeted steps. First, we utilize low-rank approximation to eliminate the redundancy within filter. This step achieves acceleration, especially in shallow layers, and also converts filters into smaller compact ones. Then, we apply channel pruning on the approximated network in a global way and obtain further benefits, especially in deep layers. In addition, we propose a spectral norm based indicator to coordinate these two steps better. Moreover, inspired by the integral idea adopted in video coding, we propose an evaluator based on Integral of Decay Curve (IDC) to judge the efficiency of various acceleration and compression algorithms. Ablation experiments and IDC evaluator prove that LAP can significantly improve channel pruning. To further demonstrate the hardware compatibility, the network produced by LAP obtains impressive speedup efficiency on the FPGA. [ABSTRACT FROM AUTHOR]