Search

Iodine is a crucial micronutrient that is indispensable for optimal physical growth and cognitive maturation. However, the dietary iodine intake status of Macao’s population is unknown. Therefore, a cross-sectional study was conducted to assess the dietary iodine intake of Macao secondary school students. Four hundred and twenty-four students filled in a self-developed, 61-item, iodine-specific food frequency questionnaire (I-FFQ). The dietary iodine intake was calculated based on the I-FFQ and food composition database. The median daily iodine intake of the students was 74.4 µg, which is lower than the 150 µg recommended by the World Health Organization (WHO). The intake frequency of dried seaweed and kelp was also low, with 49.3% and 64.2% of students consuming these foods infrequently over a month. In conclusion, the dietary iodine intake of secondary school students in Macao was inadequate. It is recommended that individuals should take the initiative to gain iodine-related knowledge. Students are advised to eat a variety of iodine-rich foods, such as seaweed and seafood, as part of a healthy, balanced diet to ensure sufficient iodine intake. Furthermore, it will be necessary to measure urinary iodine for the iodine status assessment of the Macao population in future.

The human visual system can recognize object categories accurately and efficiently and is robust to complex textures and noises. To mimic the analogy-detail dual-pathway human visual cognitive mechanism revealed in recent cognitive science studies, in this article, we propose a novel convolutional neural network (CNN) architecture named analogy-detail networks (ADNets) for accurate object recognition. ADNets disentangle the visual information and process them separately using two pathways: the analogy pathway extracts coarse and global features representing the gist (i.e., shape and topology) of the object, while the detail pathway extracts fine and local features representing the details (i.e., texture and edges) for determining object categories. We modularize the architecture and encapsulate the two pathways into the analogy-detail block as the CNN building block to construct ADNets. For implementation, we propose a general principle that transmutes typical CNN structures into the ADNet architecture and applies the transmutation on representative baseline CNNs. Extensive experiments on CIFAR10, CIFAR100, street view house numbers, and ImageNet data sets demonstrate that ADNets significantly reduce the test error rates of the baseline CNNs by up to 5.76% and outperform other state-of-the-art architectures. Comprehensive analysis and visualizations further demonstrate that ADNets are interpretable and have a better shape-texture tradeoff for recognizing the objects with complex textures.

Background: Nutritional status affects the health of the public and is one of the key factors influencing social-economic development. To date, little research on the nutritional status of the Macao university student population has been conducted. Objectives: To identify and evaluate the dietary pattern and the nutritional intake among Macao university students. Methods: The Macao students were selected by the stratified cluster random sampling method. A semi-quantitative food frequency questionnaire was used to investigate food consumption. Data were analyzed through a t-test and factor analysis by using SPSS Version 24.0. Results: A total of 1230 questionnaires were distributed. From the respondents, 1067 (86.7%) were valid. In general, we identified three major dietary patterns in this population: (1) fruit and vegetable dietary pattern, characterized by abundant consumption of fruits and vegetables; (2) grain and high fat dietary pattern, characterized as high intakes of grains and animal foods; (3) high sugar dietary pattern, characterized by a large quantity of daily sugary drinks. The average daily intake of vitamin A, thiamine, calcium, and iodine were significantly lower than the Chinese Recommended Nutrient Intake (RNI) in the subjects. Conclusions: The dietary pattern of Macao students is similar to that of other Asians. Surprisingly, the daily intake of vitamin A, thiamine, calcium, and iodine by Macao university students is significantly lower than the Chinese RNI.

Aiming at the current mainstream flying anchor payload for space debris removal, a solid thruster was proposed as the separation driving force, and a complete dynamic model of the spacecraft platform and payload were established. The effects of the gap between the directional button and the directional tube, thrust eccentricity and the initial attitude of the platform on the target accuracy under the flying anchor payload were studied. The analysis results showed that the initial attitude of the platform was the main factor affecting the target accuracy of the flying anchor payload. The control gap between 0.1mm ~ 0.25mm can effectively reduce the displacement of payload separation and the influence of disturbance on the platform.

In this paper, we propose a novel single-task continual learning framework named Bi-Objective Continual Learning (BOCL). BOCL aims at both consolidating historical knowledge and learning from new data. On one hand, we propose to preserve the old knowledge using a small set of pillars, and develop the pillar consolidation (PLC) loss to preserve the old knowledge and to alleviate the catastrophic forgetting problem. On the other hand, we develop the contrastive pillar (CPL) loss term to improve the classification performance, and examine several data sampling strategies for efficient onsite learning from ‘new’ with a reasonable amount of computational resources. Comprehensive experiments on CIFAR10/100, CORe50 and a subset of ImageNet validate the BOCL framework. We also reveal the performance accuracy of different sampling strategies when used to finetune a given CNN model. The code will be released.

In this paper, we propose a novel deep CNN-based framework to improve object detection performance. First, we introduce the Class Aware Region Proposal Network (CARPN) to produce high quality region proposals by using a new strategy for anchor generation, and by training the network with both bounding boxes and category labels of the objects. Instead of learning a binary object/non-object classifier for generating region proposals, we assign the class label to each anchor, and train the region proposal network with a multi-class loss. Second, we introduce the Focused Attention (FA) objective to encourage the network to learn features mainly from objects of interest while suppressing those features from the background region. As a result, false positive proposals caused by strong background features can be reduced to a large extent. Comprehensive experimental evaluations reveal that the proposed CARPN & FA framework remarkably outperforms the baseline Faster R-CNN method up to 4.1% mAP with a shallower network and 2.8% mAP with a deeper network, and achieves a better mAP than most of the latest state-of-the-art methods.

Deep models have shown to be vulnerable to catastrophic forgetting, a phenomenon that the recognition performance on old data degrades when a pre-trained model is fine-tuned on new data. Knowledge distillation (KD) is a popular incremental approach to alleviate catastrophic forgetting. However, it usually fixes the absolute values of neural responses for isolated historical instances, without considering the intrinsic structure of the responses by a convolutional neural network (CNN) model. To overcome this limitation, we recognize the importance of the global property of the whole instance set and treat it as a behavior characteristic of a CNN model relevant to model incremental learning. On this basis: 1) we design an instance neighborhood-preserving (INP) loss to maintain the order of pair-wise instance similarities of the old model in the feature space; 2) we devise a label priority-preserving (LPP) loss to preserve the label ranking lists within instance-wise label probability vectors in the output space; and 3) we introduce an efficient derivable ranking algorithm for calculating the two loss functions. Extensive experiments conducted on CIFAR100 and ImageNet show that our approach achieves the state-of-the-art performance.

Men who have sex with men (MSM) make up the majority of new human immunodeficiency virus (HIV) diagnoses among young people in China. Understanding HIV transmission dynamics among the MSM population is, therefore, crucial for the control and prevention of HIV infections, especially for some newly reported genotypes of HIV. This study presents a metapopulation model considering the impact of pre-exposure prophylaxis (PrEP) to investigate the geographical spread of a hypothetically new genotype of HIV among MSM in Guangdong, China. We use multiple data sources to construct this model to characterize the behavioural dynamics underlying the spread of HIV within and between 21 prefecture-level cities (i.e. Guangzhou, Shenzhen, Foshan, etc.) in Guangdong province: the online social network via a gay social networking app, the offline human mobility network via the Baidu mobility website, and self-reported sexual behaviours among MSM. Results show that PrEP initiation exponentially delays the occurrence of the virus for the rest of the cities transmitted from the initial outbreak city; hubs on the movement network, such as Guangzhou, Shenzhen, and Foshan are at a higher risk of ‘earliest’ exposure to the new HIV genotype; most cities acquire the virus directly from the initial outbreak city while others acquire the virus from cities that are not initial outbreak locations and have relatively high betweenness centralities, such as Guangzhou, Shenzhen and Shantou. This study provides insights in predicting the geographical spread of a new genotype of HIV among an MSM population from different regions and assessing the importance of prefecture-level cities in the control and prevention of HIV in Guangdong province. This article is part of the theme issue ‘Data science approach to infectious disease surveillance’.

Biotransformation of the neo-clerodane diterpene, scutebarbatine F (1), by Streptomyces sp. CPCC 205437 was investigated for the first time, which led to the isolation of nine new metabolites, scutebarbatine F1–F9 (2–10). Their structures were determined by extensive high-resolution electrospray ionization mass spectrometry (HRESIMS) and NMR data analyses. The reactions that occurred included hydroxylation, acetylation, and deacetylation. Compounds 2–4 and 8–10 possess 18-OAc fragment, which were the first examples of 13-spiro neo-clerodanes with 18-OAc group. Compounds 7–10 were the first report of 13-spiro neo-clerodanes with 2-OH. Compounds 1–10 were biologically evaluated for the cytotoxic, antiviral, and antibacterial activities. Compounds 5, 7, and 9 exhibited cytotoxic activities against H460 cancer cell line with inhibitory ratios of 46.0, 42.2, and 51.1%, respectively, at 0.3 μM. Compound 5 displayed a significant anti-influenza A virus activity with inhibitory ratio of 54.8% at 20 μM, close to the positive control, ribavirin.

Class-incremental learning (CIL) aims to incrementally learn a unified classifier for new classes emerging, which suffers from the catastrophic forgetting problem. To alleviate forgetting and improve the recognition performance, we propose a novel CIL framework, named the topological schemas model (TSM). TSM consists of a Gaussian mixture model arranged on 2D grids (2D-GMM) as the memory of the learned knowledge. To train the 2D-GMM model, we develop a novel competitive expectation-maximization (CEM) method, which contains a global topology embedding step and a local expectation-maximization fine-tuning step. Meanwhile, we choose the image samples of old classes that have the maximum posterior probability with respect to each Gaussian distribution as the episodic points. When finetuning for new classes, we propose the memory preservation loss (MPL) term to ensure episodic points still have maximum probabilities with respect to the corresponding Gaussian distribution. MPL preserves the distribution of 2D-GMM for old knowledge during incremental learning and alleviates catastrophic forgetting. Comprehensive experimental evaluations on two popular CIL benchmarks CIFAR100 and subImageNet demonstrate the superiority of our TSM.

The ability to incrementally learn new classes is crucial to the development of real-world artificial intelligence systems. In this paper, we focus on a challenging but practical few-shot class-incremental learning (FSCIL) problem. FSCIL requires CNN models to incrementally learn new classes from very few labelled samples, without forgetting the previously learned ones. To address this problem, we represent the knowledge using a neural gas (NG) network, which can learn and preserve the topology of the feature manifold formed by different classes. On this basis, we propose the TOpology-Preserving knowledge InCrementer (TOPIC) framework. TOPIC mitigates the forgetting of the old classes by stabilizing NG's topology and improves the representation learning for few-shot new classes by growing and adapting NG to new training samples. Comprehensive experimental results demonstrate that our proposed method significantly outperforms other state-of-the-art class-incremental learning methods on CIFAR100, miniImageNet, and CUB200 datasets., Accepted by CVPR 2020 (oral)

A hypercube labeling model HyperD was introduced to solve the problem of excessive bandwidth consumption and long query time between various nodes. By analyzing and adopting different strategies to improve the routing query algorithm of HyperD, a relatively more efficient routing query algorithm is proposed, which reduces the cost of communication and accelerates the data transmission between nodes. In order to verify the effectiveness of the algorithm, experiments were performed on randomly selected HyperD networks of various sizes. The improved routing algorithm was compared with the known routing algorithms, the results show that the improved algorithm is more efficient, and it can find the optimal solution in valid time.

Different from traditional text, short texts are characterized by high dimensionality, sparseness, and large text size. At the same time, some existing clustering ensemble algorithms treat each clusters equally, which will lead to the problem that the clustering results are not good enough. To solve this problem, this paper proposed a short text clustering ensemble algorithm based on convolution neural network (CNN). Firstly, the word2vec model is used to preserve the semantic relationship between words and obtain the multi-dimensional word vector representation; secondly, the feature is extracted from the original vector combining with the CNN; thirdly, clustering methods are used to cluster vectors; and then finally, Gini coefficient is used to measure the reliability of clustering, and the final clustering ensemble is carried out.

Four new oxazole-containing diterpenoids, salvianans A–D (1–4), along with three known diterpenoids (5–7), were isolated from Salvia miltiorrhiza cell cultures. The structures of the new compounds were elucidated using spectroscopic methods and single-crystal X-ray diffraction. The evaluation for their anti-HIV-1 activities revealed that 2 and 3 displayed inhibitory activities with IC50 values of 0.03 and 1.2 μM, respectively. The time of addition (TOA) assay and long terminal repeat (LTR) luciferase reporter assay results indicated that compound 2 was an HIV-1 transcription inhibitor and might be a lead compound of antiviral agents acting on HIV-1 transcription.

This paper introduces a deep model called Deep Sparse-Coding Network (DeepSCNet) to combine the advantages of Convolutional Neural Network (CNN) and sparse-coding techniques for image feature representation. DeepSCNet consists of four type of basic layers: The sparse-coding layer performs generalized linear coding for local patch within the receptive field by replacing the convolution operation in CNN into sparse-coding. The Pooling layer and the Normalization layer perform identical operations as that in CNN. And finally the Map reduction layer reduces CPU/memory consumption by reducing the number of feature maps before stacking with the following layers. These four type of layers can be easily stacked to construct a deep model for image feature learning. The paper further discusses the multi-scale, multi-locality extension to the basic DeepSCNet, and the overall approach is fully unsupervised. Compared to CNN, training DeepSCNet is relatively easier even with training set of moderate size. Experiments show that DeepSCNet can automatically discover highly discriminative feature directly from raw image pixels. HighlightsWe propose a novel deep model combining the advantages of CNN and sprase-coding technique.Image representation can be obtained directly from raw pixels.Multi-scale and Multi-Locality extensions are proposed to boost the recognition accuracy.The classification accuracy is very promising among traditional unsupervised methods.

Virtual prototyping of power electronic modules aims to allow rapid evaluation of potential designs without building and testing physical prototypes. Among the interests in thermal models of the virtual modules, process of compact thermal models needs effective methodology to fast generate small models describing the thermal performance of a potential design. This study chooses the Generalized Minimized Residual (GMRES) Algorithm to process thermal models due to its efficiency. Based on that, a machine learning aided surrogate model is proposed for the prediction of thermal performance since existing approaches take much time to determine the thermal response to a particular input power. This surrogate model is created by training a dedicated artificial neural network (ANN) on simulation data, after that this model can quickly map the module temperature and the power input in time domain. In the training process, cross-validation method is introduced to determine which neuron structure should be selected for the practical data generated by thermal equations. The test group is noted in cross-validation to give the prediction performance of structure candidates. To verify the proposed method, the resulting data of trained surrogate models are compared with the accurate simulation data after the ANN based cross-validation.

Guided by our biosynthetic hypothesis, pericoannosins C-F, four new PKS-NRPS hybrid metabolites, were discovered from the endophytic fungus Periconia sp. F-31. Their structures and absolute configurations were elucidated by extensive spectroscopic data and electronic circular dichroism analyses. Preliminary biological evaluation revealed that pericoannosins C-D exhibited anti-HIV activities with IC50 values of 15.5 and 13.5 μM. Furthermore, the bioinspired syntheses of pericoannosins C-E have also been completed with high efficiency.

With the development of 5G communication technology, the Internet of Things technology has ushered in the development opportunity. In the application of Internet of Things, spatial and social relations can be used to provide users with convenience in life and work, meanwhile there is also the risk of personal privacy disclosure. The data transmitted in the wireless network contains a large number of graph structure data, and the edge weight in weighted graph increases the risk of privacy disclosure, therefore in this paper we design a privacy protection algorithm for weighted graph, and adopts the privacy protection model to realize the privacy protection of edge weight and graph structure. Firstly, the whole graph sets are disturbed and the noises are added during the process of graph generation. Secondly, the privacy budget is allocated to protect the weight values of edges. The graph is encoded to deal with the structure of graph conveniently without separating from the information of edges, and then the disturbed edge weight is integrated into the graph. After that the privacy protection of the graph structure is realized in the process of frequent graph mining combined with differential privacy. Finally, the algorithm proposed in this paper is validated by experiments.

We develop a fine-grained image classifier using a general deep convolutional neural network (DCNN). We improve the fine-grained image classification accuracy of a DCNN model from the following two aspects. First, to better model the $h$ -level hierarchical label structure of the fine-grained image classes contained in the given training data set, we introduce $h$ fully connected (fc) layers to replace the top fc layer of a given DCNN model and train them with the cascaded softmax loss. Second, we propose a novel loss function, namely, generalized large-margin (GLM) loss, to make the given DCNN model explicitly explore the hierarchical label structure and the similarity regularities of the fine-grained image classes. The GLM loss explicitly not only reduces between-class similarity and within-class variance of the learned features by DCNN models but also makes the subclasses belonging to the same coarse class be more similar to each other than those belonging to different coarse classes in the feature space. Moreover, the proposed fine-grained image classification framework is independent and can be applied to any DCNN structures. Comprehensive experimental evaluations of several general DCNN models (AlexNet, GoogLeNet, and VGG) using three benchmark data sets (Stanford car, fine-grained visual classification-aircraft, and CUB-200-2011) for the fine-grained image classification task demonstrate the effectiveness of our method.

In this paper, we propose Transductive Semi-Supervised Deep Learning (TSSDL) method that is effective for training Deep Convolutional Neural Network (DCNN) models. The method applies transductive learning principle to DCNN training, introduces confidence levels on unlabeled image samples to overcome unreliable label estimates on outliers and uncertain samples, and develops the Min-Max Feature (MMF) regularization that encourages DCNN to learn feature descriptors with better between-class separability and within-class compactness. TSSDL method is independent of any DCNN architectures and complementary to the latest Semi-Supervised Learning (SSL) methods. Comprehensive experiments on the benchmark datasets CIFAR10 and SVHN have shown that the DCNN model trained by the proposed TSSDL method can produce image classification accuracies compatible to the state-of-the-art SSL methods, and that combining TSSDL with the Mean Teacher method can produce the best classification accuracies on the two benchmark datasets.