Multi-label learning deals with data associated with a set of labels simultaneously. Dimensionality reduction is an important but challenging task in multi-label learning. Feature selection is an efficient technique f...Multi-label learning deals with data associated with a set of labels simultaneously. Dimensionality reduction is an important but challenging task in multi-label learning. Feature selection is an efficient technique for dimensionality reduction to search an optimal feature subset preserving the most relevant information. In this paper, we propose an effective feature evaluation criterion for multi-label feature selection, called neighborhood relationship preserving score. This criterion is inspired by similarity preservation, which is widely used in single-label feature selection. It evaluates each feature subset by measuring its capability in preserving neighborhood relationship among samples. Unlike similarity preservation, we address the order of sample similarities which can well express the neighborhood relationship among samples, not just the pairwise sample similarity. With this criterion, we also design one ranking algorithm and one greedy algorithm for feature selection problem. The proposed algorithms are validated in six publicly available data sets from machine learning repository. Experimental results demonstrate their superiorities over the compared state-of-the-art methods.展开更多
Most current Global System for Mobile Communications （GSM） frequency planning methods evaluate the interference and assign frequencies based on measurement reports. Assigning the same or adjacent frequencies to cell...Most current Global System for Mobile Communications （GSM） frequency planning methods evaluate the interference and assign frequencies based on measurement reports. Assigning the same or adjacent frequencies to cells close to each other will introduce co-channel and adjacent channel interference which will reduce network performance. Traditionally, man power is used to check and allocate new frequencies which is time consuming and the accuracy is not satisfactory. This paper presents an intelligent analysis method for optimization of co-channel and adjacent channel interference by exploiting cell configuration information. The method defines an interference evaluation model by analyzing various factors such as the base station layer, the azimuth ward relationship, and the cell neighborhood relationships. The interference for each frequency is evaluated and the problem frequencies are optimized. This method is verified by a large number of actual datasets from an in-service GSM network. The results show this method has better intelligence, accuracy, timeliness, and visualization than traditional methods.展开更多
基金supported in part by the National Natural Science Foundation of China(61379049,61772120)
文摘Multi-label learning deals with data associated with a set of labels simultaneously. Dimensionality reduction is an important but challenging task in multi-label learning. Feature selection is an efficient technique for dimensionality reduction to search an optimal feature subset preserving the most relevant information. In this paper, we propose an effective feature evaluation criterion for multi-label feature selection, called neighborhood relationship preserving score. This criterion is inspired by similarity preservation, which is widely used in single-label feature selection. It evaluates each feature subset by measuring its capability in preserving neighborhood relationship among samples. Unlike similarity preservation, we address the order of sample similarities which can well express the neighborhood relationship among samples, not just the pairwise sample similarity. With this criterion, we also design one ranking algorithm and one greedy algorithm for feature selection problem. The proposed algorithms are validated in six publicly available data sets from machine learning repository. Experimental results demonstrate their superiorities over the compared state-of-the-art methods.
基金Supported by the National Key Projects of Science and Technology of China (No. 2010ZX03005-003)
文摘Most current Global System for Mobile Communications （GSM） frequency planning methods evaluate the interference and assign frequencies based on measurement reports. Assigning the same or adjacent frequencies to cells close to each other will introduce co-channel and adjacent channel interference which will reduce network performance. Traditionally, man power is used to check and allocate new frequencies which is time consuming and the accuracy is not satisfactory. This paper presents an intelligent analysis method for optimization of co-channel and adjacent channel interference by exploiting cell configuration information. The method defines an interference evaluation model by analyzing various factors such as the base station layer, the azimuth ward relationship, and the cell neighborhood relationships. The interference for each frequency is evaluated and the problem frequencies are optimized. This method is verified by a large number of actual datasets from an in-service GSM network. The results show this method has better intelligence, accuracy, timeliness, and visualization than traditional methods.
