教学课程资源库 更多>>

关键词： Autism spectrum disorder   Autism diagnostic observation schedule   Conditional random forest   Functional connectivity   fMRI   Symptom severity   Machine learning   Heterogeneity  

摘要： Autism spectrum disorders (ASDs) are heterogeneous neurodevelopmental conditions. In fMRI studies, including most machine learning studies seeking to distinguish ASD from typical developing (TD) samples, cohorts differing in gender and symptom severity composition are often treated statistically as one 'ASD group.' Using resting-state functional connectivity (FC) data, we implemented random forest to build diagnostic classifiers in four ASD samples including a total of 656 participants (N-ASD = 306,N-TD = 350, ages 6-18). Groups were manipulated to titrate heterogeneity of gender and symptom severity and partially overlapped. Each sample differed on inclusionary criteria: (1) all genders, unrestricted severity range;(2) only male participants, unrestricted severity;(3) all genders, higher severity only;and (4) only male participants, higher severity. Each set consisted of 200 participants per group (ASD, TD;matched on age and head motion): 160 for training and 40 for validation. FMRI time series from 237 regions of interest (ROIs) were Pearson correlated in a 237 x 237 FC matrix, and classifiers were built using random forest in training samples. Classification accuracies in validation samples were 62.5%, 65%, 70%, and 73.75%, respectively, for samples 1-4. Connectivity within cingulo-opercular task control (COTC) network, and between COTC ROIs and default mode and dorsal attention network contributed overall most informative features, but features differed across sets. Findings suggest that diagnostic classifiers vary depending on ASD sample composition. Specifically, greater homogeneity of samples regarding gender and symptom severity enhances classifier performance. However, given the true heterogeneity of ASDs, performance metrics alone may not adequately reflect classifier utility.

关键词： Visualization authoring tools   Interaction techniques   Cognition   Evaluation   Exploration   Creation   Presentation   Expressive  

摘要： We review the state-of-the-art interaction techniques of visualization authoring tools. The visualization tools tend to help users in the creation, exploration, or presentation of visualizations. Also, they allow users to craft expressive designs or extract data from visualizations. The review presents the interaction techniques integrated into the tools for those mentioned above five high-level goals. We cover each goal's tools and summarize how a sequence in the independent interaction techniques leads to the goal. We also discuss how well researchers had evaluated the usability and intuitiveness of interaction techniques. We aimed to reflect on the strengths and weaknesses of the evaluations. To that end, from the perspective of human cognition, we reviewed the goals, procedures, and findings of evaluations. Principally, human cognition is engaged when they perform tasks in a tool. The interaction techniques bridge the gap between human cognition and the goals they want to achieve from the tool. To sum up, in this review, we present a novel triad 'goals-interaction techniques-cognition' taxonomy. Besides, the review suggests the need for further work to enhance tools and understand users. [GRAPHICS] .

关键词： Student-faculty interactions   Career attitudes   Higher education  

摘要： This study examined the relationship between student-faculty interaction in college and students' fourth-year career attitudes toward professional success. Results suggest that some interactions with faculty, such as frequency of student-faculty interaction, are positively associated with students' fourth-year career attitudes toward professional success. Other interactions, such as personal discussions with faculty and research with a faculty member, are negatively associated with certain attitudes about professional success such as students' desire to make a lot of money. These mixed findings suggest that faculty may have a role to play in shaping students' career attitudes, but that interactions with faculty, depending on the type and context of the interaction, may encourage or discourage students' attitudes regarding professional success.

关键词： Face recognition   Single-sample per person   Dissimilarity   Image partitioning  

摘要： In single-sample face recognition (SSFR) tasks, the nearest neighbor classifier (NNC) is the most popular method for its simplicity in implementation. However, in complex situations with light, posture, expression, and obscuration, NNC cannot achieve good recognition performance when applying common distance measurements, such as the Euclidean distance. Thus, this paper proposes a novel distance measurement scheme for NNC and applies it to SSFR. The proposed method, called dissimilarity-based nearest neighbor classifier (DNNC), first segments each (training or test) image into non-overlapping patches with a given size and then generates an ordered image patch set. The dissimilarities between the given test image patch set and the training image patch sets are computed and taken as the distance measurement of NNC. The smaller the dissimilarity of image patch sets is, the closer is the distance from the test image to the training image. Therefore, the category of the test image can be determined according to the smallest dissimilarity. Extensive experiments on the AR face database demonstrate the effectiveness of DNNC, especially for the case of obscuration.

关键词： Training   Prototypes   Neural networks   Feature extraction   Task analysis   Deep learning   Adaptation models   Small-sample learning   deep neural network   relation learning   discriminative feature learning  

摘要： Despite achieving state-of-the-art performance, deep learning methods generally require a large amount of labeled data during training and may suffer from overfitting when the sample size is small. To ensure good generalizability of deep networks under small sample sizes, learning discriminative features is crucial. To this end, several loss functions have been proposed to encourage large intra-class compactness and inter-class separability. In this paper, we propose to enhance the discriminative power of features from a new perspective by introducing a novel neural network termed Relation-and-Margin learning Network (ReMarNet). Our method assembles two networks of different backbones so as to learn the features that can perform excellently in both of the aforementioned two classification mechanisms. Specifically, a relation network is used to learn the features that can support classification based on the similarity between a sample and a class prototype;at the meantime, a fully connected network with the cross entropy loss is used for classification via the decision boundary. Experiments on four image datasets demonstrate that our approach is effective in learning discriminative features from a small set of labeled samples and achieves competitive performance against state-of-the-art methods. Code is available at https://***/liyunyu08/ReMarNet.

关键词： 血液检验   血红蛋白   鉴别诊断   贫血  

摘要： 探析贫血鉴别诊断中血液检验的临床作用。方法:在我院就诊的缺铁性贫血(IDA)患者中选取102例,设为观察组,纳入时间:2018年10月~2020年9月,选取同期健康体检者102例,设为对照组,分析并对比组间检测血红蛋白(Hb)、平均红细胞血红蛋白(MCH)、红细胞体积宽度(RDW)、平均红细胞容积(MCV)、红细胞计数(RBC)。结果:观察组Hb、MCH、MCV、RBC水平较对照组低,RDW较对照组高(P<0.05)。结论:血液检验在鉴别诊断贫血中作用十分关键,可为疾病后续治疗提供有效依据,指导临床治疗工作。

关键词： Chocolate   Cocoa beans   Multi-block   Spectroscopy   Chromatography   Classification   Sensory analysis  

摘要： The present study aims at developing an analytical methodology which allows correlating sensory poles of chocolate to their chemical characteristics and, eventually, to those of the cocoa beans used for its preparation. Trained panelists investigated several samples of chocolate, and they divided them into four sensorial poles (characterized by 36 different descriptors) attributable to chocolate flavor. The same samples were analyzed by six different techniques: Proton Transfer Reaction-Time of Flight-Mass Spectrometry (PTR-ToF-MS), Solid Phase Micro Extraction-Gas Chromatography-Mass Spectroscopy (SPME-GC-MS), High-Performance Liquid Chromatography (HPLC) (for the quantification of eight organic acids), Ultra High Performance Liquid Chromatography coupled to triple-quadrupole Mass Spectrometry (UHPLC-QqQ-MS) for polyphenol quantification, 3D front face fluorescence Spectroscopy and Near Infrared Spectroscopy (NIRS). A multi-block classification approach (Sequential and Orthogonalized-Partial Least Squares - SO-PLS) has been used, in order to exploit the chemical information to predict the sensorial poles of samples. Among thirty-one test samples, only two were misclassified.

关键词： Fuel-lubricant compatibility   Oxygenate compatibility   Additive interactions  

摘要： This work empirically evaluated oxygenated blendstock - lubricant compatibility using a novel but simple method. The reactivity or compatibility was evaluated via gas chromatograph equipped with a flame ionization detector (GC-FID) before and after heating for 2 hat 150 degrees C, which would roughly mimic conditions encountered in the crankcase of a Spark Ignition (SI) or Compression-Ignition (CI) engine. Although 150 degrees C does not mimic combustion chamber temperatures, it may provide an insight of potential in-cylinder interactions. Five oxygenate blendstocks spanning several functional groups and chain lengths (prenol, isoprenol, butyl acetate, isohexanol, polyoxymethylene dimethyl ethers) were evaluated in a base fuel with nine variations of lubricant components of controlled concentrations, including fully formulated commercial lubricants. Baseline comparative examples were also generated, to decouple the effect of the oxygenate on the mixture, by heating only the base fuel with the lubricant component. Results demonstrate the relative compatibility between noted lubricants and oxygenates in base fuel upon heating. This was illustrated by minimal to no changes in the GC-FID traces. However, reactions of several of the chosen lubricants, especially Molybdenum di(2-ethylhexyl) phosphor-odithioate (Molyvan L) and zinc dialkyldithiophosphate (ZDDP), with prenol and polyoxymethylene dimethyl ethers blendstocks showed substantial side reactions compared to corresponding baseline examples. Control experiments without oxygenates but comprising the same lubricant components showed no change in the mixture with heating. We concluded the reactivity is due to the oxygenate and not the components of the base fuel. This preliminary work is valuable in establishing trends as well as providing useful information when a new component is introduced in the fuel.