Search

The performance requirement of deep learning inevitably brings up with the expense of high computational complexity and memory requirements, to make it problematic for the deployment on resource-constrained devices. Edge computing, which distributed organizes the computing node close to the data source and end-device, provides a feasible way to tackle the high-efficiency demand and substantial computational load. Whereas given edge device is resource-constrained and energy-sensitive, designing effective neural network architecture for specific edge device is urgent in the sense that deploys the deep learning application by the edge computing solution. Undoubtedly manually design the high-performing neural architectures is burdensome,let alone taking account of the resource-constraint for the specific platform. Fortunately, the success of Neural Architecture Search techniques come up with hope recently. This paper dedicate todirectly employ multi-objective NAS on the resource-constrained edge devices. We first propose the framework of multi-objectiveNAS on edge device, which comprehensively considers the performance and real-world efficiency. Our improved MobileNet-V2 search space also strikes the scalability and practicality, so that a series of Pareto-optimal architectures are received. Benefits from the directness and specialization during search procedure,our experiment on JETSON NANO shows the comparable resultwith the state-of-the-art models on ImageNet.

A fundamental bottleneck in text-to-image synthesis is that there are rarely subjective quality evaluation metrics for a single generated image. To address this issue, this paper proposed a procedure to evaluate the single generated image, which includes a specific dataset named multiple metrics quality assessment for birds(MMQA Birds) and a learning model named blind generated image evaluator(BGIE). The motivation of our proposal is twofold. On the one hand, subjective image quality evaluation is a human perceptual task; Therefore, it tends to be a process of supervised learning. To the best of our knowledge, there are not any datasets for this study. Thus, we handle this problem via designing a specific dataset. On the other hand, we observed that the spatial content of generated image attracts more attention when humans judge its quality; According to this finding, an efficient machine-learning model that combines both pixel-level features and spatial features is proposed. Extensive experiments manifest our method can solve this problem to some extent. In the generated image dataset, BGIE surpasses the state-of-art NSS-based method by 6.3% in PLCC and SRCC. In practice, we further discuss the rationality of the MMQA Birds dataset and the application of BGIE. It proves that both in subjective and objective aspects, our method achieves convincing results.

Many vector-borne viruses possess the ability to manipulate vector behaviors to facilitate their transmission. There is evidence that the mechanism of this phenomenon has been described in part as direct manipulation through regulating vector chemosensation. Rice stripe virus (RSV) is transmitted by the small brown planthopper, Laodelphax striatellus (Fallen), in a persistent, circulative–propagative manner. The effect of RSV infection on the olfactory system of L. striatellus has not been fully elucidated. Here, we employed transcriptomic sequencing to analyze gene expression profiles in antennae, legs and heads (without antennae) from L. striatellus females and males with/without RSV infection. Comparisons of the differentially expressed genes (DEGs) among antennae, legs and heads indicated that tissue-specific changes in the gene expression profile were greater than sex-specific changes. A total of 17 olfactory related genes were differentially expressed in viruliferous antennae as compared to nonviruliferous antennae, including LstrOBP4/9, LstrCSP1/2/5, LstrGR28a/43a/43a-1, LstrIR1/2/NMDA1, LstrOR67/85e/56a/94 and LstrSNMP2/2-2. There are 23 olfactory related DEGs between viruliferous and nonviruliferous legs, including LstrOBP2/3/4/12/13, LstrCSP13/5/10, LstrIR1/2/Delta2/Delta2-1/kainate2/NMDA2, LstrOR12/21/31/68 and LstrORco. A low number of olfactory related DEGs were found between viruliferous and nonviruliferous heads, including LstrCSP1, LstrOBP2, LstrOR67 and LstrSNMP2-2. Among these DEGs, the expression patterns of LstrOBP2, LstrOBP3 and LstrOBP9 in three tissues was validated by quantitative real-time PCR. The demonstration of overall changes in the genes in L. striatellus’ chemoreception organs in response to RSV infection would not only improve our understanding of the effect of RSV on the olfactory related genes of insect vectors but also provide insights into developing approaches to control the plant virus transmission and spread as well as pest management in the future.

Many vector-borne viruses possess the ability to manipulate vector behaviors to facilitate their transmission. There is evidence that the mechanism of this phenomenon has been described in part as direct manipulation through regulating vector chemosensation. Rice stripe virus (RSV) is transmitted by the small brown planthopper, Laodelphax striatellus (Fallen), in a persistent, circulative–propagative manner. The effect of RSV infection on the olfactory system of L. striatellus has not been fully elucidated. Here, we employed transcriptomic sequencing to analyze gene expression profiles in antennae, legs and heads (without antennae) from L. striatellus females and males with/without RSV infection. Comparisons of the differentially expressed genes (DEGs) among antennae, legs and heads indicated that tissue-specific changes in the gene expression profile were greater than sex-specific changes. A total of 17 olfactory related genes were differentially expressed in viruliferous antennae as compared to nonviruliferous antennae, including LstrOBP4/9, LstrCSP1/2/5, LstrGR28a/43a/43a-1, LstrIR1/2/NMDA1, LstrOR67/85e/56a/94 and LstrSNMP2/2-2. There are 23 olfactory related DEGs between viruliferous and nonviruliferous legs, including LstrOBP2/3/4/12/13, LstrCSP13/5/10, LstrIR1/2/Delta2/Delta2-1/kainate2/NMDA2, LstrOR12/21/31/68 and LstrORco. A low number of olfactory related DEGs were found between viruliferous and nonviruliferous heads, including LstrCSP1, LstrOBP2, LstrOR67 and LstrSNMP2-2. Among these DEGs, the expression patterns of LstrOBP2, LstrOBP3 and LstrOBP9 in three tissues was validated by quantitative real-time PCR. The demonstration of overall changes in the genes in L. striatellus’ chemoreception organs in response to RSV infection would not only improve our understanding of the effect of RSV on the olfactory related genes of insect vectors but also provide insights into developing approaches to control the plant virus transmission and spread as well as pest management in the future.

The rapid development of the Internet makes it easier for users to share information. On various network platforms (such as Microblog), a large amount of text data containing useful information flows every day. The visualization of these data is of great significance to cognition and use of this information. Although the current scholars have extensively studied the processing of text data and the visualization of its results, there is still confusion, monotony, etc. on the visualization of this special and widely used multi-domain text data of microblog text. We improve the traditional text data display method - word cloud and combines a 3D model to propose a new type of word cloud. Additional, we improve traditional topic model LDA and propose E-LDA to get better topics from short text data. Experiments show that we get better results in topic extraction. And in terms of the traditional word cloud, there are obvious improvements in results presentation, topic relationship presentation, and interaction friendliness.

α-Linolenic acid (ALA) is an essential fatty acid which cannot be synthesized de novo in mammals and must be ingested regularly in the diet. In this study, a microalgal strain named HDMA-11 was isolated from Lake Ming, China, and was found to accumulate a high ALA content (39.2% of total lipids). Phylogenetic neighbor-joining analysis indicated that HDMA-11 belongs to the genus Monoraphidium (Selenastraceae, Sphaeropleales) and its 18S ribosomal DNA sequence seemed to be a new molecular record of a Monoraphidium species. The fatty acid profiles, biomass productivity and lipid content of HDMA-11 were also investigated in autotrophic conditions. The high levels of polyunsaturated fatty acids in HDMA-11, especially ALA, make it suitable as a source of nutritional supplementation for human health. Furthermore, HDMA-11 exhibited good properties for biodiesel production, characterized by high lipid content (28.5% of dry weight), moderate biomass productivity (31.5 mg L−1 day−1) and a promising lipid profile.

In this paper, we propose a novel method called Segmentation Information Guidance (SIG). In this method, additional segmentation information is added to guide the process of text to complicated image synthesis. We demonstrate the effectiveness of SIG model on Microsoft Common Objects in Common (MSCOCO) dataset. It proves that the image results generated by directly using the segmentation image are more authentic and coherent than that without background.

The small brown planthopper, Laodelphax striatellus (Stal) (SBPH), is a notorious rice pest in East Asia and damages the host by feeding on the phloem and transmitting virus particles. Although SBPH relies on chemosensory perception for seeking the host, courtship, selecting oviposition sites and spreading virus particles, a systematic study of chemosensory genes in SBPH is lacking. In this study, we identified multi-gene chemosensory families from the transcriptome of SBPH olfactory organs and analyzed their expression patterns in male and female tissues. Among the chemosensory genes, 14 odorant-binding proteins (OBPs), 12 chemosensory proteins (CSPs), 7 sensory neuron membrane proteins (SNMPs) and 95 odorant receptors (ORs) were identified and annotated in SBPH olfactory organs. Based on expression profile and phylogenetic analysis, LstrOBP1, 2, 5, 6, 7, 10, LstrSNMP1, and most LstrORs showed an antennae-enriched expression pattern, which suggests an olfactory role for these genes. Relative expression of LstrOBPs was validated by quantitative real-time PCR. Our findings provide the genetic information for disrupting the feeding behavior of SBPH, which is essential for developing eco-friendly pest management technologies.

Background ω-3 polyunsaturated fatty acids (PUFAs) are synthesized from α-Linolenic acid (ALA, C18:3ω3) and play important roles in anti-inflammatory and antioxidant responses in mammal cells. ALA is an essential fatty acid which cannot be produced within the human body and must be acquired through diet. The purpose of this study was to evaluate the potential of a novel microalgal strain (HDMA-20) as a source of ω-3 PUFAs including ALA and eicosatetraenoic acid (ETA, C20:4ω3). Method Phylogenetic Neighbor-Joining analysis based on 18S ribosomal DNA sequence was used to identify the microalga strain HDMA-20. Autotrophic condition was chosen to cultivate HDMA-20 to reduce the cultivation cost. GC-MS was used to determine the fatty acid composition of HDMA-20 lipid. Results A microalgal strain (HDMA-20) from Lake Chengfeng (Daqing, Heilongjiang province, China) was found to accumulate high content of ω-3 PUFAs (63.4% of total lipid), with ALA and eicosatetraenoic acid (ETA, C20:4ω3) accounting for 35.4 and 9.6% of total lipid, respectively. Phylogenetic analysis based on 18S ribosomal DNA sequences suggested that the HDMA-20 belonged to genus Monoraphidium (Selenastraceae, Sphaeropleales) and its 18S rDNA sequence information turned out to be new molecular record of Monoraphidium species. The biomass productivity and lipid content of HDMA-20 were also investigated under autotrophic condition. The biomass productivity of HDMA-20 reached 36.3 mg L− 1 day− 1, and the lipid contents was 22.6% of dry weight. Conclusion HDMA-20 not only represent an additional source of ALA, but also a totally new source of ETA. The high content of ω-3 PUFAs, especially ALA, of HDMA-20, makes it suitable as a source of nutrition supplements for human health. In addition, HDMA-20 exhibited good properties in growth and lipid accumulation, implying its potential for cost-effective ω-3 PUFAs production in future.

Four metallated conjugated oligothiophenes, S-1, S-2, S-3 and S-4, with platinum(II) aryleneethynylenes as the electron-rich building block were synthesized to investigate their physicochemical and photovoltaic properties. These small molecules possess fairly low-lying HOMO energy levels which match with the LUMO energy level of the electron acceptor PC70BM ([6,6]-phenyl-C71-butyric acid methyl ester). Using the simple process of spin-coating solution fabrication technique, S-1:PC70BM (1:4, w/w) based organic solar cells exhibiting a high V oc of 0.913 V, with a PCE value of 0.88% were developed. In contrast, the OSC device based on S-2:PC70BM (3:7, w/w) displayed a higher PCE of 1.59% with a higher J sc value of 5.89 mA cm−2. The device based on S-4:PC70BM (1:4, w/w) exhibited a PCE value of 1.56%, with a V oc of 0.917 V.