964 research outputs found
Pseudonocardia lutea sp. nov., a novel actinobacterium isolated from soil in Chad
No full textGao, Yuhang, Piao, Chenyu, Wang, Han, Shi, Linlin, Guo, Xiaowei, Song, Jia, Xiang, Wensheng, Zhao, Junwei, Wang, Xiangjing (2018): Pseudonocardia lutea sp. nov., a novel actinobacterium isolated from soil in Chad. International Journal of Systematic and Evolutionary Microbiology 68 (6): 1992-1997, DOI: 10.1099/ijsem.0.002780, URL: http://dx.doi.org/10.1099/ijsem.0.00278
Actinomadura harenae sp. nov., a novel actinomycete isolated from sea sand in Sanya
No full textHu, Jiangmeihui, Han, Chuanyu, Yu, Bing, Zhao, Junwei, Guo, Xiaowei, Shen, Yue, Wang, Xiangjing, Xiang, Wensheng (2020): Actinomadura harenae sp. nov., a novel actinomycete isolated from sea sand in Sanya. International Journal of Systematic and Evolutionary Microbiology 70 (2): 766-772, DOI: 10.1099/ijsem.0.00381
Remote Sensing Image Scene Classification: Benchmark and State of the Art
No full text
Remote sensing image scene classification plays an important role in a wide range of applications and hence has been receiving remarkable attention. During the past years, significant efforts have been made to develop various data sets or present a variety of approaches for scene classification from remote sensing images. However, a systematic review of the literature concerning data sets and methods for scene classification is still lacking. In addition, almost all existing data sets have a number of limitations, including the small scale of scene classes and the image numbers, the lack of image variations and diversity, and the saturation of accuracy. These limitations severely limit the development of new approaches especially deep learning-based methods. This paper first provides a comprehensive review of the recent progress. Then, we propose a large-scale data set, termed "NWPU-RESISC45," which is a publicly available benchmark for REmote Sensing Image Scene Classification (RESISC), created by Northwestern Polytechnical University (NWPU). This data set contains 31 500 images, covering 45 scene classes with 700 images in each class. The proposed NWPU-RESISC45 1) is large-scale on the scene classes and the total image number; 2) holds big variations in translation, spatial resolution, viewpoint, object pose, illumination, background, and occlusion; and 3) has high within-class diversity and between-class similarity. The creation of this data set will enable the community to develop and evaluate various data-driven algorithms. Finally, several representative methods are evaluated using the proposed data set, and the results are reported as a useful baseline for future research.</p
Unsupervised 3D Local Feature Learning by Circle Convolutional Restricted Boltzmann Machine
No full text
Extracting local features from 3D shapes is an important and challenging task that usually requires carefully designed 3D shape descriptors. However, these descriptors are hand-crafted and require intensive human intervention with prior knowledge. To tackle this issue, we propose a novel deep learning model, namely circle convolutional restricted Boltzmann machine (CCRBM), for unsupervised 3D local feature learning. CCRBM is specially designed to learn from raw 3D representations. It effectively overcomes obstacles such as irregular vertex topology, orientation ambiguity on the 3D surface, and rigid or slightly non-rigid transformation invariance in the hierarchical learning of 3D data that cannot be resolved by the existing deep learning models. Specifically, by introducing the novel circle convolution, CCRBM holds a novel ring-like multi-layer structure to learn 3D local features in a structure preserving manner. Circle convolution convolves across 3D local regions via rotating a novel circular sector convolution window in a consistent circular direction. In the process of circle convolution, extra points are sampled in each 3D local region and projected onto the tangent plane of the center of the region. In this way, the projection distances in each sector window are employed to constitute a novel local raw 3D representation called projection distance distribution (PDD). In addition, to eliminate the initial location ambiguity of a sector window, the Fourier transform modulus is used to transform the PDD into the Fourier domain, which is then conveyed to CCRBM. Experiments using the learned local features are conducted on three aspects: global shape retrieval, partial shape retrieval, and shape correspondence. The experimental results show that the learned local features outperform other state-of-the-art 3D shape descriptors.</p
Bilateral K - Means algorithm for fast co-clustering
No full text
With the development of the information technology, the amount of data, e.g. text, image and video, has been increased rapidly. Efficiently clustering those large scale data sets is a challenge. To address this problem, this paper proposes a novel co-clustering method named bilateral k-means algorithm (BKM) for fast co-clustering. Different from traditional k-means algorithms, the proposed method has two indicator matrices P and Q and a diagonal matrix S to be solved, which represent the cluster memberships of samples and features, and the co-cluster centres, respectively. Therefore, it could implement different clustering tasks on the samples and features simultaneously. We also introduce an effective approach to solve the proposed method, which involves less multiplication. The computational complexity is analyzed. Extensive experiments on various types of data sets are conducted. Compared with the state-of-the-art clustering methods, the proposed BKM not only has faster computational speed, but also achieves promising clustering results. Copyright © 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.</p
Detection of Co-salient Objects by Looking Deep and Wide
No full text
In this paper, we propose a unified co-salient object detection framework by introducing two novel insights: (1) looking deep to transfer higher-level representations by using the convolutional neural network with additional adaptive layers could better reflect the sematic properties of the co-salient objects; (2) looking wide to take advantage of the visually similar neighbors from other image groups could effectively suppress the influence of the common background regions. The wide and deep information are explored for the object proposal windows extracted in each image. The window-level co-saliency scores are calculated by integrating the intra-image contrast, the intra-group consistency, and the inter-group separability via a principled Bayesian formulation and are then converted to the superpixel-level co-saliency maps through a foreground region agreement strategy. Comprehensive experiments on two existing and one newly established datasets have demonstrated the consistent performance gain of the proposed approach.</p
Two-Stage Learning to Predict Human Eye Fixations via SDAEs
No full textSaliency detection models aiming to quantitatively predict human eye-attended locations in the visual field have been receiving increasing research interest in recent years. Unlike traditional methods that rely on hand-designed features and contrast inference mechanisms, this paper proposes a novel framework to learn saliency detection models from raw image data using deep networks. The proposed framework mainly consists of two learning stages. At the first learning stage, we develop a stacked denoising autoencoder (SDAE) model to learn robust, representative features from raw image data under an unsupervised manner. The second learning stage aims to jointly learn optimal mechanisms to capture the intrinsic mutual patterns as the feature contrast and to integrate them for final saliency prediction. Given the input of pairs of a center patch and its surrounding patches represented by the features learned at the first stage, a SDAE network is trained under the supervision of eye fixation labels, which achieves both contrast inference and contrast integration simultaneously. Experiments on three publically available eye tracking benchmarks and the comparisons with 16 state-of-the-art approaches demonstrate the effectiveness of the proposed framework
Actinomadura harenae Hu, Han, Yu, Zhao, Guo, Shen, Wang & Xiang, 2020, SP. NOV.
No full textDESCRIPTION OF ACTINOMADURA HARENAE SP. NOV. Actinomadura harenae (ha.re′ nae. L. gen. n. harenae of sand). The cells of the strain are found to be Gram-positive and aerobic. White aerial mycelium is produced abundantly and differentiates into flexuous or straight spore chains consisted of cylindrical spores (0.4–0.6×0.8–1.0 µm), the spore surface is rough on ISP 3 medium. Good growth on ISP 1 agar, ISP 2 agar, ISP 3 agar, ISP 6 agar, ISP 7 agar, NA and BA media; moderate growth on ISP 4 agar; and poor growth on ISP 5 agar and CA media. The colony colours vary from brilliant yellow to grey-green yellow on agar media and the strain produces moderate olive brown soluble pigment on ISP 7 medium. Strain NEAU-Ht49 T grows at 10–45 °C (optimum, 28 °C), pH 5–10 (pH 7) and NaCl tolerance of 0–3% (0 %). Positive for decomposition of cellulose, hydrolysis of aesculin and Tweens (40 and 80) and production of urease, but negative for hydrolysis of starch and Tween 20, liquefaction of gelatin, peptonization and coagulation of milk, production of H 2 S, and reduction of nitrate. Dulcitol, D-fructose, D-glucose, meso-inositol, maltose, D-mannitol, D-mannose, L-rhamnose and sucrose are utilized as sole carbon sources, but not L-arabinose, D-galactose, lactose, raffinose, D-ribose, D-sorbitol or D-xylose. L-Alanine, L-arginine, L-asparagine, L-aspartic acid, L-glutamic acid, L-glutamine, glycine, L-proline, L-serine, L-threonine and L-tyrosine are utilized as sole nitrogen sources, but not creatine. The diagnostic diamino acid of the cell wall is meso-diaminopimelic acid. Whole-cell sugars contain glucose, madurose, mannose and ribose. The polar lipid profile consists of diphosphatidylglycerol, phosphatidylethanolamine, phosphatidylinositol, phosphatidylinositolmannoside and two unidentified lipids. The menaquinones are MK-9(H 6), MK-9(H 4) and MK-9(H 8). Major fatty acids are C 16:0, C 18:1 ω9 c, 10-methyl C 18:0 and iso- C 16:0 (>8%). The G+C content of the DNA of the type strain is 72.1 mol%. The type strain is NEAU-Ht49 T (=CGMCC 4.7499 T = JCM 32659 T), isolated from sea sand collected from Wuzhizhou island in Sanya, Hainan Province, PR China. The GenBank/ EMBL/DDBJ accession number for the 16S rRNA gene sequence of strain NEAU-Ht49 T is MK203829. This Whole Genome Shotgun project has been deposited at DDBJ/ENA/ GenBank under the accession number RFFG00000000. The version described in this paper is version RFFG01000000.1.Published as part of Hu, Jiangmeihui, Han, Chuanyu, Yu, Bing, Zhao, Junwei, Guo, Xiaowei, Shen, Yue, Wang, Xiangjing & Xiang, Wensheng, 2020, Actinomadura harenae sp. nov., a novel actinomycete isolated from sea sand in Sanya, pp. 766-772 in International Journal of Systematic and Evolutionary Microbiology 70 (2) on page 771, DOI: 10.1099/ijsem.0.003819, http://zenodo.org/record/374503
Query-dependent metric learning for adaptive, content-based image browsing and retrieval
No full textContent-based image retrieval (CBIR) systems often incorporate a relevance feedback mechanism in which retrieval is adapted based on users identifying images as relevant or irrelevant. Such relevance decisions are often assumed to be category-based. However, forcing a user to decide upon category membership of an image, even when unfamiliar with a database and irrespective of context, is restrictive. An alternative is to obtain user feedback in the form of relative similarity judgments. The ability of a user to provide meaningful feedback depends on the interface that displays retrieved images and facilitates the feedback. Similarity-based 2D layouts provide context and can enable more efficient visual search. Motivated by these observations, this study describes and evaluates an interactive image browsing and retrieval approach based on relative similarity feedback obtained from 2D image layouts. It incorporates online maximal-margin learning to adapt the image similarity metric used to perform retrieval. A user starts a session by browsing a collection of images displayed in a 2D layout. He/she may choose a query image perceived to be similar to the envisioned target image. A set of images similar to the query are then returned. The user can then provide relational feedback and/or update the query image to obtain a new set of images. Algorithms for CBIR are often characterised empirically by simulating usage based on pre-defined, fixed category labels, deeming retrieved results as relevant if they share a category label with the query. In contrast, the purpose of the system in this study is to enable browsing and retrieval without predefined categories. Therefore evaluation is performed in a target-based setting by quantifying the efficiency with which target images are retrieved given initial queries
Osimertinib as induction therapy for oligometastatic non-small cell lung cancer with EGFR mutation: a case report
No full textBACKGROUND: The role of surgery in combined modality therapy for selected stage IV oligometastatic (OM) non-small cell lung cancer (NSCLC) is still controversial. Tyrosine kinase inhibitors (TKIs) targeting epidermal growth factor receptor (EGFR) significantly improved the survival in adjuvant therapy in metastatic NSCLC but has rare evidence in inductive setting. This is the first case report about uniportal video-assisted thoracic surgery after induction therapy of TKI for OM-NSCLC. CASE DESCRIPTION: A 50-year-old Chinese woman presented to hospital with headache and blurred vision and was diagnosed with an intracranial tumor. The craniotomy confirmed the metastasis from primary lung cancer. Positron emission tomography/computed tomography (PET/CT) showed the mass located in the left upper lobe and left hilar lymph node involvement. Next-generation sequencing found an EGFR mutation (exon 21 p.L858R missense), and osimertinib, a third-generation TKI, was used 80 mg per day as the induction therapy due to the EGFR mutation detected from the metastatic tumor. A favorable treatment response was observed of the lung tumor with lymph node regression, followed by uniportal thoracoscopic left upper lobectomy and systematic lymphadenectomy. The postoperative pathology evaluated both the lung lesion and lymph nodes and confirmed the OM status of this patient. No complications were observed and postoperative osimertinib 80 mg per day continued. CONCLUSIONS: Our case suggests that the role of surgery should be appropriately reevaluated for EGFR-mutated OM-NSCLC with the emerging development of EGFR-TKI
- …
