Medical images are valuable for clinical diagnosis and decision making. Image modality is an important primary step, as it is capable of aiding clinicians to access required medical image in retrieval systems. Traditional methods of modality classification are dependent on the choice of hand-crafted features and demand a clear awareness of prior domain knowledge. The feature learning approach may detect efficiently visual characteristics of different modalities, but it is limited to the number of training datasets. To overcome the absence of labeled data, on the one hand, we take deep convolutional neural networks (VGGNet, ResNet) with different depths pre-trained on ImageNet, fix most of the earlier layers to reserve generic features of natural images, and only train their higher-level portion on ImageCLEF to learn domain-specific features of medical figures. Then, we train from scratch deep CNNs with only six weight layers to capture more domain-specific features. On the other hand, we employ two data augmentation methods to help CNNs to give the full scope to their potential characterizing image modality features. The final prediction is given by our voting system based on the outputs of three CNNs. After evaluating our proposed model on the subfigure classification task in ImageCLEF2015 and ImageCLEF2016, we obtain new, state-of-the-art results-76.87% in ImageCLEF2015 and 87.37% in ImageCLEF2016-which imply that CNNs, based on our proposed transfer learning methods and data augmentation skills, can identify more efficiently modalities of medical images.

Learners in a massive open online course often express feelings, exchange ideas and seek help by posting questions in discussion forums. Due to the very high learner-to-instructor ratios, it is unrealistic to expect instructors to adequately track the forums, find all of the issues that need resolution and understand their urgency and sentiment. In this paper, considering the biases among different courses, we propose a transfer learning framework based on a convolutional neural network and a long short-term memory model, called ConvL, to automatically identify whether a post expresses confusion, determine the urgency and classify the polarity of the sentiment. First, we learn the feature representation for each word by considering the local contextual feature via the convolution operation. Second, we learn the post representation from the features extracted through the convolution operation via the LSTM model, which considers the long-term temporal semantic relationships of features. Third, we investigate the possibility of transferring parameters from a model trained on one course to another course and the subsequent fine-tuning. Experiments on three real-world MOOC courses confirm the effectiveness of our framework. This work suggests that our model can potentially significantly increase the effectiveness of monitoring MOOC forums in real time.

Abstract. Rocky desertification is a major ecological problem of land degradation in karst areas. In these areas, the high soil calcium (Ca) content has become an important environmental factor that can affect the restoration of vegetation. Consequently, the screening of plant species that can adapt to high Ca soil environments is a critical step in vegetation restoration. In this study, three grades of rocky desertification sample areas were selected in karst areas of southwestern Hunan, China (LRD: light rocky desertification; MRD: moderate rocky desertification; and IRD: intense rocky desertification). Each grade of these sample areas had three sample plots in different slope positions, each of which had four small quadrats (one in rocky-side areas, three in non-rocky-side areas). We measured the Ca content of leaves, branches, and roots from 41 plant species, as well as soil total Ca (TCa) and exchangeable Ca (ECa) at depths of 0–15, 15–30, and 30–45 cm in each small quadrat. The results showed that the soil Ca2+ content in rocky-side areas was significantly higher than that in non-rocky-side areas (p<0.05). The mean soil TCa and ECa content increased gradually along with the grade of rocky desertification, in the order IRD > MRD > LRD. For all plant functional groups, the plant Ca content of aboveground parts was significantly higher than that of the belowground parts (p<0.05). The soil ECa content had significant effects on plant Ca content of the belowground parts but had no significant effects on plant Ca content of the aboveground parts. Of the 41 plant species that were sampled, 17 were found to be dominant (important value > 1). The differences in Ca2+ content between the aboveground and belowground parts of the 17 dominant species were calculated, and their correlations with soil ECa content were analyzed. The results showed that these 17 species can be divided into three categories: Ca-indifferent plants, high-Ca plants, and low-Ca plants. These findings provide a vital theoretical basis and practical guide for vegetation restoration and ecosystem reconstruction in rocky desertification areas.

Abstract:Compound figure detection on figures and associated captions is the first step to making medical figures from biomedical literature available for further analysis. The performance of traditional methods is limited to the choice of hand-engineering features and prior domain knowledge. We train multiple convolutional neural networks (CNNs), long short-term memory (LSTM) networks, and gated recurrent unit (GRU) networks on top of pre-trained word vectors to learn textual features from captions and employ deep CNNs to learn visual features from figures. We then identify compound figures by combining textual and visual prediction. Our proposed architecture obtains remarkable performance in three run types-textual, visual and mixed-and achieves better performance in ImageCLEF2015 and ImageCLEF2016.