| 文章名称 | 作者排序 | 发表刊物 | 发表日期 | 期刊类型 | 备注 |
|---|
|
Adaptive Learning Emotion Identification Method of ShortTexts for Online Medical Knowledge Sharing Community
|
第三作者 |
Computational Intelligence and Neuroscience |
2019/6/25 |
期刊论文SCI |
e medical knowledge sharing community pr...展开 |
e medical knowledge sharing community provides users with an open platform for accessing medical resources and sharingmedical knowledge, treatment experience, and emotions. Compared with the recipients of general commodities, the recipients inthe medical knowledge sharing community pay more attention to the intensity or overall evaluation of emotional vocabularies inthe comments, such as treatment effects, prices, service attitudes, and other aspects. ,erefore, the overall evaluation is not a keyfactor in medical service comments, but the semantics of the emotional polarity is the key to affect recipients of the medicalinformation. In this paper, we propose an adaptive learning emotion identification method (ALEIM) based on mutual in-formation feature weight, which captures the correlation and redundancy of features. In order to evaluate the proposed method’seffectiveness, we use four basic corpus libraries crawled from the Haodf’s online platform and employ Taiwan University NTUSDSimplified Chinese Emotion Dictionary for emotion classification. ,e experimental results show that our proposed ALEIMmethod has a better performance for the identification of the low-frequency words’ redundant features in comments of the onlinemedical knowledge sharing community.1.IntroductionMore and more comments, opinions, suggestions, ratings,and feedback are produced on social networks with the rapiddevelopment of the Internet [1]. While those on social net-works are meant to be useful, this part of the contents requiresadopting text mining and emotion analysis techniques. Untilnow, emotional analysis and evaluation still face severalchallenges [2], which are shown in Table 1. ,ese challengesbecome obstacles to accurately analyze emotional polarity.In recent years, more and more research has been doneon emotion analysis. Among them, unstructured naturallanguage texts have received the widest attention of scholars[9]. Emotion analysis is the inference of users’ opinions,positions, and attitudes through written or spoken contents[10]. Solving emotion analysis tasks typically usesdictionary-based and learning-based approach [11, 12]. ,edictionary-based approach analyzes the relevance of eachword to a particular emotion by using the predefined dic-tionary [13]. Learning-based methods typically use labeledsamples to train the specific-purpose models under super-vision [14].Emotional analysis is increasingly used to analyze humanemotions, but the fatal shortcoming of current emotionanalysis methods is lack of aspect level granularity improve-ment, and also they are rarely applied to online knowledgecommunities, especially medical knowledge communities, soit is necessary to find an emotional classification method formedical knowledge communities. In light of these consider-ations, we propose an adaptive learning emotion identificationmethod (ALEIM) based on mutual information featureweight, which captures the correlation and redundancy offeatures. Its effectiveness is verified on the datasets crawledfrom the Haodf’s online platform, in which the eigenvaluescorresponding to the feature nouns are assigned according tothe收起 |
|
Improved Cost-Sensitive SupportVector Machine Classifier forBreast Cancer Diagnosis
|
第三作者 |
athematical Problems in Engineering |
2018/11/28 |
期刊论文SCI |
As one of the most prevalent cancers amo...展开 |
As one of the most prevalent cancers among women worldwide, breast cancer has attracted the most attention by researchers. It hasbeen verified that an accurate and early detection of breast cancer can increase thechances for the patients to take the right treatmentplan and survive for a long time. Nowadays, numerous classification methods have been utilized for breast cancer diagnosis.However, most of these classification models have concentrated on maximum the classification accuracy, failed to take into accountthe unequal misclassification costs for the breast cancer diagnosis. To the best of our knowledge, misclassifying the cancerous patientas non-cancerous has much higher cost compared to misclassifying the non-cancerous as cancerous. Consequently, in order totackle this deficiency and further improve the classification accuracy of the breast cancer diagnosis, we propose an improved cost-sensitive support vector machine classifier (ICS-SVM) for the diagnosis of breast cancer. In the proposed approach, we take fullaccount of unequal misclassification costs of breast cancer intelligent diagnosis and provide more reasonable results over previousworks and conventional classification models. To evaluate the performance of the proposed approach, Wisconsin Breast Cancer(WBC) and Wisconsin Diagnostic Breast Cancer (WDBC) breast cancer datasets obtained from the University of California atIrvine (UCI) machine learning repository have been studied. The experimental results demonstrate that the proposed hybridalgorithm outperforms all the existing methods. Promisingly, the proposed method can be regarded as a useful clinical tool forbreast cancer diagnosis and could also be applied to other illness diagnosis.收起 |
|
A novel intelligent classification model for breast cancer diagnosis
|
第三作者 |
InformationProcessingandManagement |
2018/10/18 |
期刊论文核心期刊 |
|
|
基于互信息的贝叶斯－案例检索特征选择模型
|
第一作者 |
工业工程与管理 |
2018/10/15 |
期刊论文CSSCI |
案例检索过程中案例集存在特征冗余，使得检索效率和准确度较低。传 统 的 基 于 ...展开 |
案例检索过程中案例集存在特征冗余，使得检索效率和准确度较低。传 统 的 基 于 贝 叶斯 网 络 案 例 检 索 特 征 选 择 模 型（ＢＮ－ＣＢＲ）对 先 验 知 识 利 用 效 率 不 高，且不能有效选择消除冗余性的特 征 子 集。构 建 基 于 互 信 息 的 贝 叶 斯－案例检索特征选择模型（ＭＩ－ＢＮＣＢＲ），采 用 特 征 冗 余 度 和互 信 息 计 算 案 例 特 征 的 综 合 权 重，改 善ＢＮ－ＣＢＲ模型对先验知识利用效率不高的问题，其 采 用 互信息方法可消除案例集中的冗余特征并得到最优特征子集，采 用 基 于 远 端 最 近 距 离 计 算 的Ｋ－Ｄ树方 法 进 一 步 改 善 基 于 互 信 息 的 贝 叶 斯－案 例 检 索 的 效 率，并利用医学基准数据进行实验，结 果 表 明所引入的方法有效地提高了案例检索的准确度和检索效率。收起 |
|
Knowledge Sharing of Online Health Community Based on Cognitive Neuroscience
|
第三作者 |
NEUROQUANTOLOGY |
2018/4/19 |
期刊论文SSCI |
|
|
基于互信息判据的智能制造资源配置效能研究
|
第一作者 |
计算机集成制造系统 |
2017/9/1 |
期刊论文EI |
|
|
基于案例-规则检索的特征阈值选择模型
|
第一作者 |
情报学报 |
2017/3/1 |
期刊论文CSSCI |
|
|
数据驱动的医疗与健康决策支持研究综述
|
第一作者 |
工业工程与管理 |
2017/2/1 |
期刊论文CSSCI |
|
|
Temporal case matching with information value maximization for predicting physiological states
|
其他 |
Information Sciences |
2016/6/1 |
期刊论文SCI |
|
|
Ambiguity Multi-attribute Decisions with Evidential Chains-based Fusion Reasoning Method
|
其他 |
Journal of Information & Computational Science |
2015/12/1 |
期刊论文EI |
|
|
Heterogeneous entity classification with case-based reasoning and relative frequencies
|
第一作者 |
Journal of Computational Information Systems |
2015/11/1 |
期刊论文EI |
|
|
Random disturbance reasoning model of decision-making system and its anti-interference capability
|
其他 |
International Journal of Industrial Engineering |
2015/5/1 |
期刊论文EI |
|
|
基于ＴＡＮ的最小决策损失诊断模型及其推理机制
|
第一作者 |
工业工程与管理 |
2014/4/10 |
期刊论文CSSCI |
|
|
New approach to eliminate structural redundancy in case resource pools using a mutual information
|
第一作者 |
Journal of Systems Engineering and Electronics |
2013/8/1 |
期刊论文EI |
|
|
贝叶斯信息融合及其在心脏病诊断中的应用
|
第一作者 |
工业工程与管理 |
2013/8/1 |
期刊论文CSSCI |
|
|
New Algorithm for CBR-RBR Fusion with Robust Thresholds
|
第一作者 |
CHINESE JOURNAL 0F MECHANICAL ENGINEERING |
2012/6/1 |
期刊论文EI |
|
| 合计发表 16 篇论文 |