自适应融合层级特征的混合退化图像复原算法

多种退化类型混合的图像比单一类型的退化图像降质更严重,很难建立精确模型对其复原,研究端到端的神经网络算法是复原的关键.现有的基于操作选择注意力网络的算法(operation-wiseattentionnetwork,OWAN)虽然有一定的性能提升,但是其网络过于复杂,运行较慢,复原图像缺乏高频细节,整体效果也有提升的空间.针对这些问题,提出一种基于层级特征融合的自适应复原算法.该算法直接融合不同感受野分支的特征,增强复原图像的结构;用注意力机制对不同层级的特征进行动态融合,增加模型的自适应性,降低了模型冗余;另外,结合L1损失和感知损失,增强了复原图像的视觉感知效果.在DIV2K,BSD500等数据集上的实验结果表明,该算法无论是在峰值信噪比和结构相似性上的定量分析,还是在主观视觉质量方面,均优于OWAN算法,充分证明了该算法的有效性.     

Multiobjective PSO based adaption of neural network topology for pixel classification in satellite imagery

The proposed work involves the multiobjective PSO based adaption of optimal neural network topology for the classification of multispectral satellite images. It is per pixel supervised classification using spectral bands (original feature space). This paper also presents a thorough experimental analysis to investigate the behavior of neural network classifier for given problem. Based on 1050 number of experiments, we conclude that following two critical issues needs to be addressed: (1) selection of most discriminative spectral bands and (2) determination of optimal number of nodes in hidden layer. We propose new methodology based on multiobjective particle swarm optimization (MOPSO) technique to determine discriminative spectral bands and the number of hidden layer node simultaneously. The accuracy with neural network structure thus obtained is compared with that of traditional classifiers like MLC and Euclidean classifier. The performance of proposed classifier is evaluated quantitatively using Xie-Beni and β indexes. The result shows the superiority of the proposed method to the conventional one.     

基于时频域的卷积神经网络运动想象脑电信号识别方法

针对目前运动想象脑电（EEG）信号识别率较低的问题，考虑到脑电信号蕴含着丰富的时频信息，提出一种基于时频域的卷积神经网络（CNN）运动想象脑电信号识别方法。首先，利用短时傅里叶变换（STFT）对脑电信号的相关频带进行预处理，并将多个电极的时频图组合构造出一种二维时频图；然后，针对二维时频图的时频特性，通过一维卷积的方法设计了一种新颖的CNN结构；最后，通过支持向量机（SVM）对CNN提取的特征进行分类。基于BCI数据集的实验结果表明，所提方法的平均识别率为86.5%，优于其他传统运动想象脑电信号识别方法；同时将该方法应用在智能轮椅上，验证了其有效性。     

Characterizing physical habitat preferences and thermal refuge occupancy of brook trout (Salvelinus fontinalis) and Atlantic salmon (Salmo salar) at high river temperatures

Anthropogenic influences, including climate change, are increasing river temperatures in northern and temperate regions and threatening the thermal habitats of native salmonids. When river temperatures exceed the tolerance levels of brook trout and Atlantic salmon, individuals exhibit behavioural thermoregulation by seeking out cold‐water refugia – often created by tributaries and groundwater discharge. Thermal infrared (TIR) imagery was used to map cold‐water anomalies along a 53 km reach of the Cains River, New Brunswick. Trout and salmon parr did not use all identified thermal anomalies as refugia during higher river temperature periods (>21°C). Most small‐bodied trout (8–30 cm) were observed in 80% of the thermal anomalies sampled. Large‐bodied trout (>35 cm) required a more specific set of physical habitat conditions for suitable refugia, that is, 100% of observed large trout used 30% of the anomalies sampled and required water depths >65 cm within or adjacent to the anomaly. Densities of trout were significantly higher within anomalies compared with areas of ambient river temperature. Salmon parr were less aligned with thermal anomalies at the observed temperatures, that is, 59% were found in 65% of the sampled anomalies; and densities were not significantly different within/ outside anomalies. Salmon parr appeared to aggregate at 27°C, and after several events over 27°C variability in aggregation behaviour was observed – some fish aggregated at 25°C, others did not. We stipulate this is due to variances of thermal fatigue. Habitat suitability curves were developed for velocity, temperature, depth, substrate, and deep water availability to characterize conditions preferred by fish during high‐temperature events. These findings are useful for managers as our climate warms, and can potentially be used as a tool to help conserve and enhance thermal refugia for brook trout and Atlantic salmon in similar systems.     

一种改进的图像域SAR目标散射中心特征提取方法

散射中心是SAR图像目标识别的重要特征。本文基于属性散射中心模型，在文献[6]的基础上，提出了一种改进的图像域SAR目标散射中心特征提取方法。在该方法中，通过引入参数规则化处理步骤，解决了属性散射中心特征提取方法的收敛问题，提高了属性散射中心特征参数估计的精度和效率；提出了一种能同时实现散射中心数目确定和结构判别的方法，实现了散射中心类型的可靠判别。仿真数据和MSTAR实测SAR图像数据的实验结果，验证了本文改进的图像域SAR目标散射中心特征提取方法的有效性。     

Configurational and nonconfigurational interactions between odorants in binary mixtures.

Studies on odor mixture perception suggest that although odor components can often be identified in mixtures, mixtures can also give rise to novel perceptual qualities that are not present in the components. Using an olfactory habituation task, the authors evaluated how the perceptual similarity between components in a mixture affects the perceptual quality of the mixture itself. Rats perceived binary mixtures composed of similar components as different from their 2 components, whereas binary mixtures composed of dissimilar components were perceived as very similar to their components. Results show that for both types of mixtures, pretraining to Component A reduces subsequent learning about Component B in rats trained in the presence of A. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Differentiating visual and kinesthetic imagery in mental practice.

Through two experiments, the study sought to emphasize the usefulness of the visual and kinesthetic imagery in mental practice. In Experiment 1, it was hypothesized that when the task to be learned through mental practice necessitates the reproduction of a form by drawing, the visual image, which provides a wide span of apprehension, is more suitable than the kinesthetic image. On the other hand, the kinesthetic image that supplies inputs from the muscles' positions and movements should be more appropriate for the acquisition of the duration of the drawing. In Experiment 2, it was hypothesized that the task, transformed into a motor task necessitating minute coordination of the two hands, would benefit more from kinesthetic imagery. To have optimal control over what was actually experienced during mental practice, the participants' imagery skills were measured. The participants also benefited from prior imagery training. The results demonstrate that when using mental practice to initially acquire a task, visual imagery is better for tasks that emphasize form while kinesthetic imagery is better for those tasks that emphasize timing or minute coordination of the two hands. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Pure perceptual-based sequence learning.

Learning a sequence of target locations when the sequence is uncorrelated with a sequence of responses and target location is not the response dimension (pure perceptual-based sequence learning) was examined. Using probabilistic sequences of target locations, the author shows that such learning can be implicit, is unaffected by distance between target locations, and is mostly limited to first-order transition probabilities. Moreover, the mechanism underlying learning affords processing of information at anticipated target locations and appears to be attention based. Implications for hypotheses of implicit sequence learning are discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Achievement of specificational information usage with true and false feedback in learning a visual relative-mass discrimination task.

Participants' usage of informational variables in learning visual relative-mass discrimination in collisions was tracked by means of PROBIT correlations. Four groups received feedback that was true or accorded with either of three nonspecificational cue variables. A majority in each group adopted the feedback, but several participants defied the false feedback. Unlike in previous research, the fit to data of the relative-mass invariant could not be bettered by post hoc linear combinations of the cues. Discriminability was lower in the use of the invariant. Analytic complexity was rejected as an explanation for discriminability differences. A "smart mechanism" for pickup of the relative-mass invariant was developed as an extension of G. Johansson's (1950/1994) vector model. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

想象热刺激和实际热刺激脑功能成像研究

本实验用功能性核磁共振成像技术（fMRI）对人想象热刺激和实际接受热刺激进行了研究。这是继想象冷刺激和实际接受冷刺激实验之后的另一个关于想象刺激与实际接受刺激的实验、实验结果发现想象热刺激与实际热刺激激活脑区既有相同之处也有不同之处。想象热刺激激活了初级体感区（SI）、左侧额上回、左侧额中回、运动区和扣带回。实际热刺激激活了初级体感区（SI）区、右侧额上回、右侧额中回、运动区。区别在于额叶和扣带回,这个结论与想象冷刺激和实际冷刺激实验的结论几乎相同,只是两种情况下在额叶的具体差别不同。