基于Adaboost方法的实时人眼定位

人眼定位在基于机器视觉的疲劳检测系统中起着至关重要的作用。该文介绍了Adaboost方法在人眼定位中的应用,首先描述了Adaboost的基本思想,使用人脸分类器对人脸进行定位,之后在人脸定位的基础上使用人眼分类器最终定位人眼,实现了实时的人眼定位。     

基于案例推理的研究综述

该文对人工智能领域的一个分支——基于案例的推理技术做了简要概述,包括CBR的原理和组成。评述了CBR近年来的理论发展和应用发展。并对未来发展方向做出了预测。     

基于改进Multi-Agent系统的基因表达数据的分析与研究

通过介绍改进的多代理系统在分析基因表达数据中的应用,揭示了运用普通分类器找出有效的分类基因,而且这些普通分类器在研究基因表达数据库时可被代理使用.这样就可得到一个具有大量基因特征的小子集,并且用它可以帮助辨认病人的临床状况和特征.实验表明代理通过改进和相互协作可改进其性能,并通过两个著名的基因表达问题来展示项目的研究成果,而且使得量度的准确性在维数增加时变得不很敏感.     

空地联合反导预警技术探讨

由于战术弹道导弹作战方式的特殊性,要求建立一个多层次的、完善的预警系统。指出了地基相控阵雷达探测战术弹道导弹的优点与存在的局限性,对空基预警机系统预警探测的特点作了分析。提出了地基相控阵雷达和预警机空地联合反导预警方式,按照系统集成的方法,建立了联合反导预警装备系统的数学模型,仿真分析了系统的探测效能,为联合反导预警体系的构建提供了参考依据。     

最小海明距离分类器的字符识别方法研究

应用最小海明距离(Hamming Distance,缩写HD)分类器,研制了一种新型的基于最小海明分类器的字符识别方法。讨论了该字符识别方法实现的技术路线,较好解决了理论的工程化应用问题,对500帧连续图像的时间字符进行实验,时间字符识别准确率为99.8%,达到了字符比较准确识别的目的。     

伪实例与人工标注实例相结合的词义消歧方法

知识获取是制约基于语料库的词义消歧方法性能提高的瓶颈,使用等价伪词的自动语料标注方法是近年来解决该问题的有效方法。等价伪词是用来代替歧义词在语料中查找消歧实例的词。但使用等价伪词获得的部分伪实例质量太差,且无法为没有或很少同义词的歧义词确定等价伪词。基于此,该文提出一种将等价伪词获得的伪实例和人工标注实例相结合的词义消歧方法。该方法通过计算伪实例与歧义词上下文的句子相似度,删除质量低下的伪实例。并借助人工标注语料为某些无等价伪词的歧义词提供消歧实例,计算各义项的分布概率。在Senseval-3汉语消歧任务上的实验中,该文方法取得了平均F-值为0.79的成绩。     

特征权对贝叶斯分类器文本分类性能的影响

在文本分类研究中,人们希望用特征权来改善文本分类效果。以最优分类器——贝叶斯分类器为基准分类器,研究了特征权对文本分类性能的可能影响。理论推导表明,就最优分类器而言,特征权不能有效提高文本分类效果。     

面向应用型本科的“计算机控制系统”课程教学改革与探索

应用型本科院校以培养高素质应用型人才作为培养目标。为达到预期的培养目标,需要在专业培养方案设置、课程知识体系、课程教学模式与方法等各个环节进行有针对性的优化设计。《计算机控制系统》课程兼有深入的理论基础和面向实际应用的特点,因此在教学改革时需要把握好理论与实践的关系。针对理论教学,在优化调整讲授内容的基础上,通过引入工程案例法将核心知识点串联起来,并制作“慕课”形式的教学视频作为线下教学的补充;针对实验教学,设置更多的设计性和综合性实验并引入三级训练项目作为补充。改革后的教学内容与工程实践的结合更加紧密,教学素材与方法也更加丰富,极大地提升了学生的学习自主性,更有利于学生分析和解决实际问题能力的培养。     

BS-SC Model: A Novel Method for Predicting Child Abuse Using Borderline-SMOTE Enabled Stacking Classifier

For a long time, legal entities have developed and used crime prediction methodologies. The techniques are frequently updated based on crime evaluations and responses from scientific communities. There is a need to develop type-based crime prediction methodologies that can be used to address issues at the subgroup level. Child maltreatment is not adequately addressed because children are voiceless. As a result, the possibility of developing a model for predicting child abuse was investigated in this study. Various exploratory analysis methods were used to examine the city of Chicago’s child abuse events. The data set was balanced using the Borderline-SMOTE technique, and then a stacking classifier was employed to ensemble multiple algorithms to predict various types of child abuse. The proposed approach successfully predicted crime types with 93% of accuracy, precision, recall, and F1-Score. The AUC value of the same was 0.989. However, when compared to the Extra Trees model (17.55), which is the second best, the proposed model’s execution time was significantly longer (476.63). We discovered that Machine Learning methods effectively evaluate the demographic and spatial-temporal characteristics of the crimes and predict the occurrences of various subtypes of child abuse. The results indicated that the proposed Borderline-SMOTE enabled Stacking Classifier model (BS-SC Model) would be effective in the real-time child abuse prediction and prevention process.     

An Ophthalmic Evaluation of Central Serous Chorioretinopathy

Nowadays in the medical field, imaging techniques such as Optical Coherence Tomography (OCT) are mainly used to identify retinal diseases. In this paper, the Central Serous Chorio Retinopathy (CSCR) image is analyzed for various stages and then compares the difference between CSCR before as well as after treatment using different application methods. The first approach, which was focused on image quality, improves medical image accuracy. An enhancement algorithm was implemented to improve the OCT image contrast and denoise purpose called Boosted Anisotropic Diffusion with an Unsharp Masking Filter (BADWUMF). The classifier used here is to figure out whether the OCT image is a CSCR case or not. 150 images are checked for this research work (75 abnormal from Optical Coherence Tomography Image Retinal Database, in-house clinical database, and 75 normal images). This article explicitly decides that the approaches suggested aid the ophthalmologist with the precise retinal analysis and hence the risk factors to be minimized. The total precision is 90 percent obtained from the Two Class Support Vector Machine (TCSVM) classifier and 93.3 percent is obtained from Shallow Neural Network with the Powell-Beale (SNNWPB) classifier using the MATLAB 2019a program.