关于在指纹自动识别系统中把性别信息作为指纹特征的几点思考

指纹性别信息就是指纹自动识别系统中捺印指纹数据库里的人员或现场指印数据库里的现场指印遗留人的性别情况即男女情况，目前指纹自动识别系统还没有把数据库里的指纹对应的人员或遗留人的性别信息作为指纹特征进行标注、入库并运用于比对中，笔者在指纹查档破案实践中认为把数据库里指纹数据对应的人员或遗留人的性别信息作为捺印指纹或现场指印特征进行标注、入库并运用于比对中可提高指纹查档效果。

一种基于性别的说话人索引算法

为了提高说话人索引准确率,对说话人改变判决中常用的贝叶斯信息判决(BIC)进行改进和在说话人辨认中使用性别信息,提出了一种基于性别的说话人索引算法。首先使用惩罚距离公式对说话人改变进行检测,解决了在说话人改变判决中使用BIC需要不断调节惩罚因子的问题;其次在说话人改变检测的基础上,采用性别模型判断每个说话人的性别;最后把男性和女性说话人分别对待,使用说话人模型自举法对说话人进行辨认。实验结果表明:在说话人改变检测中,采用惩罚距离公式,和BIC相比不需要调整参数,和DISTBIC相比,在F1方面提高了2%;在说话人辨认方面,利用性别信息,说话人索引准确率(SIA)提高了20.93%,说话人数量准确率(SNA)方面提高了3%。

一种两步判决的说话人分割算法

为了提高说话人分割(SS)准确率,该文综合考虑了静音信息和性别信息在SS中的作用,提出了一种两步判决的SS算法。在从音频流中分离出语音段的基础上,采用两步判决的方法进行SS。第1步采用基频信息为主、性别模型为辅的策略进行SS,将相邻说话人基频差异大的说话人改变检测出来;第2步采用基于性别的改进T2判决公式进行SS,实现相邻说话人基频差异小的同性别SS,为此,该文提出了一个基于块的潜在说话人改变点检测算法。实验结果表明,本文算法提高了分割准确率,F1度量值可达85.14%。对于短时长(<2s)语音段的SS,该算法和传统的贝叶斯信息判决算法相比,漏检率减少了16%。

Identification of contamination source in water distribution network based on consumer complaints

A new methodology was proposed for contamination source identification using information provided by consumer complaints from a probabilistic view.Due to the high uncertainties of information derived from users,the objective of the proposed methodology doesn't aim to capture a unique solution,but to minimize the number of possible contamination sources.In the proposed methodology,all the possible pollution nodes are identified through the CSA methodology firstly.And then based on the principle of total probability formula,the probability of each possible contamination node is obtained through a series of calculation.According to magnitude of the probability,the number of possible pollution nodes is minimized.The effectiveness and feasibility of the methodology is demonstrated through an application to a real case of ZJ City.Four scenarios were designed to investigate the influence of different uncertainties on the results in this case.The results show that pollutant concentration,injection duration,the number of consumer complaints nodes used for calculation and the prior probability with which consumers would complaint have no particular effect on the identification of contamination source.Three nodes were selected as the most possible pollution sources in water pipe network of ZJ City which includes more than 3 000 nodes.The results show the potential of the proposed method to identify contamination source through consumer complaints.

Research of New Concept Sonar—Cognitive Sonar

The performance of a sonar system is closely related to the marine environment and the target characteristics. When dealing with the echoes of a traditional active sonar system, the sonar designers often do not take into account the influence of the environmental information and prior knowledge perceived by sonar receivers, making it difficult to obtain desired processing results. Based on the basic principle and key technology of sonar, this paper proposed a cognition-based intelligent sonar system in theory--cognitive sonar. Cognitive sonar is capable of jointly optimizing the transmission waveform and receiver according to the changes of environment so that its detection and identification performance can be significantly improved.

Artistic Practices [Between] Gender and Technologies

This paper was carried out by the group of professors--Maia Creus, Tamara Diaz, and Ines Martins from the Design Analysis and Prospective Department, with the collaboration of the Catalan Institute for Women, Generalitat de Catalunya. Maia Creus and Ines Martins are parts of the research group TADD （Theory, Analysis, Design, and Development） recognized by Ramon Llull University. The research, based on feminist and performance studies, focuses on artistic groups currently working in Catalonia and whose practices produce tools and technology sharing, highlight the social and educational potential of ICTs （information and communication technologies） free access when used, consciously and critically, from feminist perspectives assumed. The research project was developed as a dual methodological process. This research group has developed a critical review of the three conceptual axes--women, art, and technology--around which revolves the present study and, in parallel, has conducted field work directly with groups of selected artists, in order to meet them within their areas of production and to know more about their working methods, theoretical discourse, goals, frustrations, and desires. This deployment in parallel was used to develop a group of key concepts that revolve around ＂free culture＂ and ＂culture of access＂ that in contrast with the practices and theories of the investigated groups are necessary to intercept and reinterpret. Through various forms of visibility, this paper intends to investigate, promote, and share these tools, technologies, and pedagogies developed by these groups which, by its own dynamics of collective work, as well as the processes of public participation, emphasize forms of interculturality and interdisciplinary.

Application of fuzzy logic in weighted information of fusion fingerprints and palm prints

It is a developing job to distinguish identifications with information fusion of fingerprints and palm prints. It is also a very effective way to resolve the problem of low identification rate and low stability of single biology characteristic identification. Based on the theory of fuzzy logic theory, we bring out the method of obfuscating weigh coefficient and reliability to fuse the information of fingerprints and palm prints to realize high identification rate. The experiment proves the feasibility and effectiveness of this method and the identification rate can be more than 90%, which contributes useful experience to the research of identification using biology characteristics.

Effects of Gender and Other Factors on Agricultural Commercialization in Peri-urban and Rural Cassava Farms of Rivers State, Nigeria

The study was designed to investigate into the level of cassava commercialization, extent of gender effects and other factors on household commercialization index （HCI） of cassava in both rural and peri-urban areas of Rivers State, Nigeria. The study used a stratified random sampling technique to select 50 cassava farmers each from Etche and Ekwerre LGAs of the state （i.e. 100 farmers in all）. A set of structured questionnaire and interview schedule was used to retrieve information from the farmers. Data analysis was done using descriptive statistics, Chow test and truncated regression analysis model based on Maximum Likelihood derived from Censored Normal or TOBIT approach. It was found that significant difference exist in the HC1 of rural farmers （49%） and peri-urban （40%）. The drivers of HCI varied across the areas but on the whole it was noted that gender, farm size, distance to market, labour, farming experience, price of cassava and access to market information signiftcantly influenced the probability of expanding the scale of commercialization of cassava in the area. It was recommended that government and interested bodies should give priority to women in designing and implementing cassava commercialization programmes policies that will improve farmers access to land and also help build on capacities of the farmers to commercialize such as access to extension service, establishment of market information service （MIS）, development of market and transport infrastructure were recommended too.

Research on the Pragmatics of Politeness Principle of Bulletin Board System based on the Differences of Gender and Habits

In this paper, we conduct research on the pragmatics of politeness principle of bulletin board system based on the differences of gender and habits. The openness of the Internet makes all kinds of information received into the vision of an equal chance and web sites in order to improve the hit rate which causes the traffic of commercial purposes such as tabloidization tend to be more negative news spread. To strengthen the research of network language management strategy, it has very important theoretical significance and practical meaning analyzed. Our proposed methodology will help researchers to understand the approaches to use the pragrnatics of politeness.

Fault Diagnosis Based on MultiKernel Classification and Information Fusion Decision

In machine learning and statistics, classification is the a new observation belongs, on the basis of a training set of data problem of identifying to which of a set of categories （sub-populations） containing observations （or instances） whose category membership is known. SVM （support vector machines） are supervised learning models with associated learning algorithms that analyze data and recognize patterns, used for classification and regression analysis. The basic SVM takes a set of input data and predicts, for each given input, which of two possible classes fon^as the output, making it a non-probabilistic binary linear classifier. In pattern recognition problem, the selection of the features used for characterization an object to be classified is importance. Kernel methods are algorithms that, by replacing the inner product with an appropriate positive definite function, impticitly perform a nonlinear mapping 4~ of the input data in Rainto a high-dimensional feature space H. Cover＇s theorem states that if the transformation is nonlinear and the dimensionality of the feature space is high enough, then the input space may be transformed into a new feature space where the patterns are linearly separable with high probability.