No abstract

Attribute reduction is a key data preprocessing technique, and has been widely studied in data mining, machine learning, and granular computing. Minimal test cost attribute reduction is one of important parts researched in cost-sensitive learning. The backtracking algorithm can obtain an optimal reduct, however on only small datasets due to the NP-hardness of the problem. Heuristic algorithms, such as the genetic one and the information gain based one, are employed to deal with this problem. In this paper, we propose the Fast Randomized Algorithm to obtain a satisfactory reduct more efficiently. The focus of the algorithm is a randomization mechanism that deals with attributes addition and deletion. There are two important parameters in the addition stage, namely the selecting probability of attributes and the number of selected attributes per batch. We obtain some appropriate parameter settings through experiments in a variety of datasets. Results show that the optimal settings of two parameters rarely change on different datasets. Our algorithm is more stable and significantly more efficient than existing heuristic ones.

Coal gangue has the shortcomings of low calorific value and refractory burnout, while polyvinyl chloride has the advantages of a long combustion process and high calorific value. In order to make up for these shortcomings of coal gangue, the possibility of a treatment method based on co-combustion of coal gangue with polyvinyl chloride, which can be centrally recovered from municipal solid waste, is proposed. In order to analyze the combustion effect of a mixture of these two substances, experimental samples were prepared by mixing these two substances in three different ratios, and they were tested by thermogravimetric analysis. The experimental results were compared, analyzed and evaluated. The effects of the proportion of polyvinyl chloride in the mixture on the temperature parameters, activation energy, and interaction during co-combustion were analyzed. In order to analyze the interaction during co-combustion of the two, a coupling analysis method for mixed combustion is presented, and the effectiveness of this method is verified by comparing with the correlation analysis results of co-combustion. The results show that co-combustion can mitigate the ignition difficulty and burnout of coal gangue. When the proportion of polyvinyl chloride in the mixture was increased from 20% to 80%, the maximum weightlessness rate of the first stage rapidly increased from 4.5%/min to 15.6%/min; however, that of the second stage slowly increased from 3.7%/min to 4.2%/min. A 20% proportion of polyvinyl chloride showed the most significant promotion of co-combustion, with a maximum coupling coefficient of 0.00318, which was 1.11 and 1.35 times greater than that of 50% and 80% proportions, respectively. Co-combustion can reduce the activation energy of coal gangue during the initial and end stages. Therefore, co-combustion is helpful to improve the problems of low calorific value and refractory burnout of coal gangue.