Communication leads to bacterial heterogeneous adaptation to changing conditions in partial nitrification reactor.

Recently, it is reported that bacterial communication coordinates the whole consortia to jointly resist the adverse environments. Here, we found the bacterial communication inevitably distinguished bacterial adaptation among different species in partial nitrification reactor under decreasing temperatures. We operated a partial nitrification reactor under temperature gradient from 30 °C to 5 °C and found the promotion of bacterial communication on adaptation of ammonia-oxidizing bacteria (AOB) was greater than that of nitrite-oxidizing bacteria (NOB). Signal pathways with single-component sensing protein in AOB can regulate more genes involved in bacterial adaptation than that with two-component sensing protein in NOB. The negative effects of bacterial communication, which were seriously ignored, have been highlighted, and Clp regulator downstream diffusible signal factor (DSF) based signal pathways worked as transcription activators and inhibitors of adaptation genes in AOB and NOB respectively. Bacterial communication can induce differential adaptation through influencing bacterial interactions. AOB inclined to cooperate with DSF synthesis bacteria as temperature declined, however, cooperation between NOB and DSF synthesis bacteria inclined to get weakening. According to the regulatory effects of signal pathways, bacterial survival strategies for self-protection were revealed. This study hints a potential way to govern niche differentiation in the microbiota by bacterial communication, contributing to forming an efficient artificial ecosystem.

Blue-light irradiation induced partial nitrification.

The role of ray radiation from the sunlight acting on organisms has long-term been investigated. However, how the light with different wavelengths affects nitrification and the involved nitrifiers are still elusive. Here, we found more than 60 % of differentially expressed genes (DEGs) in nitrifiers were observed under irradiation of blue light with wavelengths of 440-480 nm, which were 13.4 % and 20.3 % under red light and white light irradiation respectively. Blue light was more helpful to achieve partial nitrification rather than white light or red light, where ammonium oxidization by ammonia-oxidizing archaea (AOA) with the increased relative abundance from 8.6 % to 14.2 % played a vital role. This was further evidenced by the enhanced TCA cycle, reactive oxygen species (ROS) scavenge and DNA repair capacity in AOA under blue-light irradiation. In contrast, nitrite-oxidizing bacteria (NOB) was inhibited severely to achieve partial nitrification, and the newly discovered encoded blue light photoreceptor proteins made them more sensitive to blue light and hindered cell activity. Ammonia-oxidizing bacteria (AOB) expressed genes for DNA repair capacity under blue-light irradiation, which ensured their tiny impact by light irradiation. This study provided valuable insights into the photosensitivity mechanism of nitrifiers and shed light on the diverse regulatory by light with different radiation wavelengths in artificial systems, broadening our comprehension of the nitrogen cycle on earth.

Automated vessel specific coronary artery calcification quantification with deep learning in a large multi-center registry.

AIMS: Vessel specific coronary artery calcification (CAC) is additive to global CAC for prognostic assessment. We assessed accuracy and prognostic implications of vessel-specific automated deep learning (DL) CAC analysis on electrocardiogram gated and attenuation correction computed tomography (CT) in a large multicenter registry. METHODS AND RESULTS: Vessel-specific CAC was assessed in the left main/left anterior descending (LM/LAD), left circumflex (LCX) and right coronary artery (RCA) using a DL model trained on 3000 gated CT and tested on 2094 gated CT and 5969 non-gated attenuation correction CT. Vessel-specific agreement was assessed with linear weighted Cohen's Kappa for CAC zero, 1-100, 101-400 and >400 Agatston units (AU). Risk of major adverse cardiovascular events (MACE) was assessed during 2.4±1.4 years follow-up, with hazard ratios (HR) and 95% confidence intervals (CI). There was strong to excellent agreement between DL and expert ground truth for CAC in LM/LAD, LCX and RCA on gated CT [0.90 (95% CI 0.89 to 0.92); 0.70 (0.68 to 0.73); 0.79 (0.77 to 0.81)] and attenuation correction CT [(0.78 (0.77 to 0.80); 0.60 (0.58 to 0.62); 0.70 (0.68 to 0.71)]. MACE occurred in 242 (12%) undergoing gated CT and 841(14%) of undergoing attenuation correction CT. LM/LAD CAC >400 AU was associated with the highest risk of MACE on gated (HR 12.0, 95% CI 7.96, 18.0, p<0.001) and attenuation correction CT (HR 4.21, 95% CI 3.48, 5.08, p<0.001). CONCLUSION: Vessel-specific CAC assessment with DL can be performed accurately and rapidly on gated CT and attenuation correction CT and provides important prognostic information.

Communication mediated interaction between bacteria and microalgae advances photogranulation.

Recently, photogranules composed of bacteria and microalgae for carbon-negative nitrogen removal receive extensive attention worldwide, yet which type of bacteria is helpful for rapid formation of photogranules and whether they depend on signaling communication remain elusive. Varied signaling communication was analyzed using metagenomic method among bacteria and microalgae in via of two types of experimentally verified signaling molecule from bacteria to microalgae, which include indole-3-acetic acid (IAA) and N-acyl homoserine lactones (AHLs) during the operation of photo-bioreactors. Signaling communication is helpful for the adaptability of bacteria to survive with algae. Compared with non-signaling bacteria, signaling bacteria more easily adapt to the varied conditions, evidenced by the increased abundance in the operated reactors. Signaling bacteria are easier to enter the phycosphere, and they dominate the interactions between bacteria and algae rather than non-signaling bacteria. The co-abundance groups (CAGs) with signaling bacteria possess higher abundance than that without signaling bacteria (22.27 % and 6.67 %). Importantly, signaling bacteria accessibly interact with microalgae, which possess higher degree centralities and 32.50 % of them are keystone nodes in the network, in contrast to only 18.66 % of non-signaling bacteria. Thauera carrying both IAA and AHLs synthase genes are highly enriched and positively correlated with nitrogen removal rate. Our work not only highlights the essential roles of signaling communication between microalgae and bacteria in the development of photogranules, but also enriches our understanding of microbial sociobiology.

Chameleon-like Anammox Bacteria for Surface Color Change after Suffering Starvation.

Bacteria are often exposed to long-term starvation during transportation and storage, during which a series of enzymes and metabolic pathways are activated to ensure survival. However, why the surface color of the bacteria changes during starvation is still not well-known. In this study, we found black anammox consortia suffering from long-term starvation contained 0.86 mmol gVSS-1 cytochrome c, which had no significant discrepancy compared with the red anammox consortia (P > 0.05), indicating cytochrome c was not the key issue for chromaticity change. Conversely, we found that under starvation conditions cysteine degradation is an important metabolic pathway for the blackening of the anammox consortia for H2S production. In particular, anammox bacteria contain large amounts of iron-rich nanoparticles, cytochrome c, and other iron-sulfur clusters that are converted to produce free iron. H2S combines with free iron in bacteria to form Fe-S compounds, which eventually exist stably as FeS2, mainly in the extracellular space. Interestingly, FeS2 could be oxidized by air aeration, which makes the consortia turn red again. The unique self-protection mechanism makes the whole consortia appear black, avoiding inhibition by high concentrations of H2S and achieving Fe storage. This study expands the understanding of the metabolites of anammox bacteria as well as the bacterial survival mechanism during starvation.

Fast Broad Multiview Multi-Instance Multilabel Learning (FBM3L) With Viewwise Intercorrelation.

Multiview multi-instance multilabel learning (M3L) is a popular research topic during the past few years in modeling complex real-world objects such as medical images and subtitled video. However, existing M3L methods suffer from relatively low accuracy and training efficiency for large datasets due to several issues: 1) the viewwise intercorrelation (i.e., the correlations of instances and/or bags between different views) are neglected; 2) the diverse correlations (e.g., viewwise intercorrelation, interinstance correlation, and interlabel correlation) are not jointly considered; and 3) high computation burden for training process over bags, instances, and labels across different views. To resolve these issues, a novel framework called fast broad M3L (FBM3L) is proposed with three innovations: 1) utilization of viewwise intercorrelation for better modeling of M3L tasks while existing M3L methods have not considered; 2) based on graph convolutional network (GCN) and broad learning system (BLS), a viewwise subnetwork is newly designed to achieve joint learning among the diverse correlations; and 3) under BLS platform, FBM3L can learn multiple subnetworks jointly across all views with significantly less training time. Experiments show that FBM3L is highly competitive (or even better than) in all evaluation metrics up to 64% in average precision (AP) and much faster than most M3L (or MIML) methods (up to 1030 times), especially on large multiview datasets ( ≥ 260 K objects).

Bacterial Communication Coordinated Behaviors of Whole Communities to Cope with Environmental Changes.

Bacterial communication plays an important role in coordinating microbial behaviors in a community. However, how bacterial communication organizes the entire community for anaerobes to cope with varied anaerobic-aerobic conditions remains unclear. We constructed a local bacterial communication gene (BCG) database comprising 19 BCG subtypes and 20279 protein sequences. BCGs in anammox-partial nitrification consortia coping with intermittent aerobic and anaerobic conditions as well as gene expressions of 19 species were inspected. We found that when suffering oxygen changes, intra- and interspecific communication by a diffusible signal factor (DSF) and bis-(3'-5')-cyclic dimeric guanosine monophosphate (c-di-GMP) changed first, which in turn induced changes of autoinducer-2 (AI-2)-based interspecific and acyl homoserine lactone (AHLs)-based intraspecific communication. DSF and c-di-GMP-based communication regulated 455 genes, which covered 13.64% of the genomes and were mainly involved in antioxidation and metabolite residue degradation. For anammox bacteria, oxygen influenced DSF and c-di-GMP-based communication through RpfR to upregulate antioxidant proteins, oxidative damage-repairing proteins, peptidases, and carbohydrate-active enzymes, which benefited their adaptation to oxygen changes. Meanwhile, other bacteria also enhanced DSF and c-di-GMP-based communication by synthesizing DSF, which helped anammox bacteria survive at aerobic conditions. This study evidences the role of bacterial communication as an "organizer" within consortia to cope with environmental changes and sheds light on understanding bacterial behaviors from the perspective of sociomicrobiology.

Potential bacterial isolation by dosing metabolites in cross-feedings.

Metabolic cross-feeding, in which species use metabolites of other members to promote their own growth, is vital for bacterial growth and survival. Thus, whether the unculturable bacteria can be isolated or purified from consortia by adding these essential metabolites remains elusive. In this study, mass spectrometry imaging vividly pictured symbionts supplied folate and gluconate to anammox bacteria to support their growth. After dosing folate and gluconate, the relative abundance and activity of anammox bacteria were substantially improved. Such enhancement is originated from the added folate and gluconate significantly eased metabolic burden of anammox bacteria as they no longer secreted the extracellular public goods to others for "resource exchange" during cross-feedings. On the other hand, the decreased supplement of extracellular "public goods" lead to the decay of symbionts with high demand for these metabolites in the consortia. This also deservedly increased the relative abundance of anammox bacteria. This study provides a new dimension to isolate specific functional bacteria based on metabolic cross-feedings.

Composite carrier enhanced bacterial adhesion and nitrogen removal in partial nitrification/anammox process.

The rapid start-up and stable operation of one-stage (Partial nitrification/anammox) PN/A process for low-ammonium wastewater are difficult to be achieved, and many carriers are designed to solve this problem. Here, a composite carrier was developed, in which sepiolite and non-woven fabrics were assembled in polypropylene spherical shells. At the start-up phase, PA reactor using the composite carriers reached a higher nitrogen removal rate of 134.50 ± 19.60 mg·N·L-1d-1, in contrast to that of 48.85 ± 19.64 mg·N·L-1d-1 in the PB reactor without sepiolite carriers. When the final influent ammonium concentration of PN/A process is 100 mg/L, the total nitrogen removal efficiency can reach 72 ± 0.03 %. High biomass immobilization ability of composite carrier was evidenced by the greater adsorption trend between sludge and sepiolite than that between sludge and non-woven fabrics, where hydrophobic interaction and Van der Waals interaction played a major role. Extracellular protein (PN) content and the ratio of PN and extracellular polysaccharide of samples in PA were significantly higher than those in PB, verifying higher biofilm formation ability on the composite carrier. The composite carrier also increased the abundance of dominant bacteria in PN/A process, especially AOB, the relative abundance of which reached 46.11 %. And it increased the abundance of essential functional genes for nitrogen conversion as their perfect acid neutralizing effects. This study is of great significance in improving the start-up speed and stable operation of this process.

Missing-view completion for fatty liver disease detection.

Fatty liver disease is a common disease that causes extra fat storage in an individual's liver. Patients with fatty liver disease may progress to cirrhosis and liver failure, further leading to liver cancer. The prevalence of fatty liver disease ranges from 10% to 30% in many countries. In general, detecting fatty liver requires professional neuroimaging modalities or methods such as computed tomography, ultrasound, and medical experts' practical experiences. Considering this point, finding intelligent electronic noninvasive diagnostic approaches are desired at present. Currently, most existing works in the area of computerized noninvasive disease detection often apply one view (modality) or perform multi-view (several modalities) analysis, e.g., face, tongue, and/or sublingual for disease detection. The multi-view data of patients provides more complementary information for diagnosis. However, due to the conditions of data acquisition, interference by human factors, etc., many multi-view data are defective with some missing-view information, making these multi-view data difficult to evaluate. This factor largely affects the performance of classifying disease and the development of fully computerized noninvasive methods. Thus, the purpose of this study is to address the missing view issue among noninvasive disease detection. In this work, a multi-view dataset containing facial, sublingual vein, and tongue images are initially processed to produce corresponding feature for incomplete multi-view disease diagnostic evaluation. Hereby, we propose a novel method, i.e., multi-view completion, to process the incomplete multi-view data in order to complete the missing-view information for classifying fatty liver disease from healthy candidates. In particular, this method can explore the intra-view and inter-view information to produce the missing-view data effectively. Extensive experiments on a collected dataset with 220 fatty liver patients and 220 healthy samples show that our proposed approach achieves better diagnostic results with missing-view completion compared to the original incomplete multi-view data under various classifiers. Related results prove that our method can effectively process the missing-view issue and improve the noninvasive disease detection performance.

Fuzzy Graph Subspace Convolutional Network.

Graph convolutional networks (GCNs) are a popular approach to learn the feature embedding of graph-structured data, which has shown to be highly effective as well as efficient in performing node classification in an inductive way. However, with massive nongraph-organized data existing in application scenarios nowadays, it is critical to exploit the relationships behind the given groups of data, which makes better use of GCN and broadens the application field. In this article, we propose the fuzzy graph subspace convolutional network (FGSCN) to provide a brand-new paradigm for feature embedding and node classification with graph convolution (GC) when given an arbitrary collection of data. The FGSCN performs GC on the fuzzy subspace ( F -space), which simultaneously learns from the underlying subspace information in the low-dimensional space as well as its neighborliness information in the high-dimensional space. In particular, we construct the fuzzy homogenous graph GF on the F -space by fusing the homogenous graph of neighborliness GN and homogenous graph of subspace GS (defined by the affinity matrix of the low-rank representation). Here, it is proven that the GC on F -space will propagate both the local and global information through fuzzy set theory. We evaluated FGSCN on 15 unique datasets with different tasks (e.g., feature embedding, visual recognition, etc.). The experimental results showed that the proposed FGSCN has significant superiority compared with current state-of-the-art methods.

Response of amino acid metabolism to decreased temperatures in anammox consortia: Strong, efficient and flexible.

Although amino acid (AA) metabolism is basis of bacterial activities, unique characteristics of its response to decreased temperatures are not fully understood. Achieving nitrogen removal rate of 130-150 mg N/ (L∙d), metabolic differences of anammox consortia between 35 °C and four decreased temperatures (15-30 °C) were revealed respectively. 0-11.4-fold abundance variation of marker metabolites evidenced change of key metabolism (metabolism of AA, lipid and energy production) at decreased temperatures. However, AA metabolism varied more obviously than others, implying stronger response and higher functional potential. Efficiently, network topology confirmed more cellular processes represented by growth metabolism and biofilm formation were influenced by AA metabolism. Flexibly, down-regulated biosynthesis of unfavorable AAs for psychrophilic enzyme differed from enhanced biosynthesis of costly AAs, which only matched partial decreased temperatures to save energy. This work elucidates advantages of AA metabolism over others, exogenous amino acids could significantly promote activity of anammox bacteria at decreased temperatures.

Cross-feeding among microalgae facilitates nitrogen recovery at low C/N.

Although co-culture of microalgae has been found as a feasible strategy to improve biomass production, their interspecies relationships are not fully understood. Here, two algae taxa, Chlorella sp. and Phormidium sp., were mono-cultured and co-cultured in three photobioreactors for 70 days with periodically harvesting to investigate how dual-species interaction influence nitrogen recovery. Results showed that the co-culture system achieved a significantly higher protein production and nitrogen removal rate than those in the individual cultures at a C/N ratio of 3:1 (p < 0.05). Genome-Centered metagenomic analysis revealed their cooperative relationship exemplified by cross-feeding. Phormidium sp. had the ability to synthesize pseudo-cobalamin, and Chlorella sp. harbored the gene for remodeling the pseudo-cobalamin to bioavailable vitamin B12. Meanwhile, Chlorella sp. could contribute the costly amino acid and cofactors for Phormidium sp. Their symbiotic interaction facilitated extracellular polymeric substances (EPS) production and nitrogen recovery. The EPS concentration in co-culture was positively related to the settling efficiency (R2 = 0.774), which plays an essential role in nitrogen recovery. This study provides new insights into microbial interactions among the photoautotrophic community and emphasizes the importance of algal interspecies interaction in algae-based wastewater treatment.

Consensus Sparsity: Multi-context Sparse Image Representation via L∞-induced Matrix Variate.

The sparsity is an attractive property that has been widely and intensively utilized in various image processing fields (e.g., robust image representation, image compression, image analysis, etc.). Its actual success owes to the exhaustive mining of the intrinsic (or homogenous) information from the whole data carrying redundant information. From the perspective of image representation, the sparsity can successfully find an underlying homogenous subspace from a collection of training data to represent a given test sample. The famous sparse representation (SR) and its variants embed the sparsity by representing the test sample using a linear combination of training samples with L0-norm regularization and L1-norm regularization. However, although these state-of-the-art methods achieve powerful and robust performances, the sparsity is not fully exploited on the image representation in the following three aspects: 1) the within-sample sparsity, 2) the between-sample sparsity, and 3) the image structural sparsity. In this paper, to make the above-mentioned multi-context sparsity properties agree and simultaneously learned in one model, we propose the concept of consensus sparsity (Con-sparsity) and correspondingly build a multi-context sparse image representation (MCSIR) framework to realize this. We theoretically prove that the consensus sparsity can be achieved by the L∞-induced matrix variate based on the Bayesian inference. Extensive experiments and comparisons with the state-of-the-art methods (including deep learning) are performed to demonstrate the promising performance and property of the proposed consensus sparsity.

Two-phase non-invasive multi-disease detection via sublingual region.

Non-invasive multi-disease detection is an active technology that detects human diseases automatically. By observing images of the human body, computers can make inferences on disease detection based on artificial intelligence and computer vision techniques. The sublingual vein, lying on the lower part of the human tongue, is a critical identifier in non-invasive multi-disease detection, reflecting health status. However, few studies have fully investigated non-invasive multi-disease detection via the sublingual vein using a quantitative method. In this paper, a two-phase sublingual-based disease detection framework for non-invasive multi-disease detection was proposed. In this framework, sublingual vein region segmentation was performed on each image in the first phase to achieve the region with the highest probability of covering the sublingual vein. In the second phase, features in this region were extracted, and multi-class classification was applied to these features to output a detection result. To better represent the characterisation of the obtained sublingual vein region, multi-feature representations were generated of the sublingual vein region (based on color, texture, shape, and latent representation). The effectiveness of sublingual-based multi-disease detection was quantitatively evaluated, and the proposed framework was based on 1103 sublingual vein images from patients in different health status categories. The best multi-feature representation was generated based on color, texture, and latent representation features with the highest accuracy of 98.05%.

Multi-feature representation for burn depth classification via burn images.

Burns are a common and severe problem in public health. Early and timely classification of burn depth is effective for patients to receive targeted treatment, which can save their lives. However, identifying burn depth from burn images requires physicians to have a lot of medical experience. The speed and precision to diagnose the depth of the burn image are not guaranteed due to its high workload and cost for clinicians. Thus, implementing some smart burn depth classification methods is desired at present. In this paper, we propose a computerized method to automatically evaluate the burn depth by using multiple features extracted from burn images. Specifically, color features, texture features and latent features are extracted from burn images, which are then concatenated together and fed to several classifiers, such as random forest to generate the burn level. A standard burn image dataset is evaluated by our proposed method, obtaining an Accuracy of 85.86% and 76.87% by classifying the burn images into two classes and three classes, respectively, outperforming conventional methods in the burn depth identification. The results indicate our approach is effective and has the potential to aid medical experts in identifying different burn depths.

Computational Traditional Chinese Medicine diagnosis: A literature survey.

BACKGROUND AND OBJECTIVE: Traditional Chinese Medicine (TCM) diagnosis is based on the theoretical principles and knowledge, where it is steeped in thousands of years of history to diagnose various types of diseases and syndromes. It can be generally divided into four main diagnostic approaches: 1. Inspection, 2. Auscultation and olfaction, 3. Inquiry, and 4. Palpation, which are widely used in TCM hospitals in China and around the world. With the development of intelligent computing technology in recent years, computational TCM diagnosis has grown rapidly. METHODS: In this paper, we aim to systematically summarize the development of computational TCM diagnosis based on four diagnostic approaches, mainly focusing on digital acquisition devices, collected datasets, and computational detection approaches (algorithms). Furthermore, all related works of this field are compared and explored in detail. RESULTS: This survey provides the principles, applications, and current progress in computing for readers and researchers in terms of computational TCM diagnosis. Moreover, the future development direction, prospect, and technological trend of computational TCM diagnosis will also be discussed in this study. CONCLUSIONS: Recent computational TCM diagnosis works are compared in detail to show the pros/cons, where we provide some meaningful suggestions and opinions on the future research approaches in this area. This work is useful for disease detection in computational TCM diagnosis as well as health management in the smart healthcare area. INDEX TERMS: Computational diagnosis, Traditional Chinese Medicine, survey, smart healthcare.

Graph Based Multichannel Feature Fusion for Wrist Pulse Diagnosis.

It is well known in Traditional Chinese Medicine (TCM) that a person's wrist pulse signal can reflect their health condition. Recently, many computerized wrist pulse AI systems have been proposed to simulate a practitioner's three fingers in order to acquire the wrist pulse signals (three positions/channels) from a candidate's wrist dynamically, before evaluating their health status based on the various feature extraction and detection methods. However, few works have investigated the correlation of the extracted features from the three wrist channels and comprehensively fused the various features together, which can improve the performance of wrist pulse diagnosis. In this paper, we propose a graph based multichannel feature fusion (GBMFF) method to utilize the multichannel features of the wrist pulse signals effectively. In detail, two different sensors, i.e., pressure and photoelectricity are used to capture the three channels of the wrist pulse signals. These are used to generate two different features by applying the stacked sparse autoencoder and wavelet scattering. Each feature of one wrist pulse sample is regarded as a node associated with its corresponding feature vector, and used to construct a graph for one candidate. A novel algorithm is implemented to construct different graphs for different candidates, which are used for wrist pulse diagnosis by developing graph convolutional networks. Experimental results indicate that our proposed AI-based method can obtain superior performances compared to other state-of-the-art approaches.

[Effect of sandblasting combined with femtosecond laser-etching on surface physicochemical properties of pure titanium].

PURPOSE: The aim of this study was to generate periodic microstructures on pure titanium surface by femtosecond laser-etching after sandblasting, and to assess the physicochemical properties of its surface. METHODS: Twelve pure titanium discs with diameter of 10 mm and thickness of 4 mm were used and divided into 3 groups according to different surface treatment methods: group S (sandblasting surface), group SA (sandblasting surface with acid-etching), and group SL (sandblasting surface with femtosecond laser-etching). Scanning electron microscopy (SEM) was used to observe the surface morphology. X-ray energy spectrum(EDS) was used to observe the surface chemical compositions. Three dimensional surface topography and surface roughness were evaluated by laser scanning confocal microscope (CLSM). The static contact angle was detected by high temperature wetting angle measuring instrument. SPSS19.0 software package was used for statistical analysis. RESULTS: SEM and CLSM showed well-distributed periodic and cyclic microstructure which formed second-order roughness composite structure in group SL. EDS analysis showed that the Al element on SL surface decreased (group SL 4.37%group SA 0.32>group S 0). Surface roughness analysis showed that surface roughness significantly increased in group SL [group SL (7.33±0.38)µm>group SA (1.08±0.12)µm>group S (1.05±0.14)µm](P<0.001). Static contact angle analysis showed that the static contact angle of surface was significantly reduced in group SL [group SL (34.4±2.5)°

A shell dataset, for shell features extraction and recognition.

Shells are very common objects in the world, often used for decorations, collections, academic research, etc. With tens of thousands of species, shells are not easy to identify manually. Until now, no one has proposed the recognition of shells using machine learning techniques. We initially present a shell dataset, containing 7894 shell species with 29622 samples, where totally 59244 shell images for shell features extraction and recognition are used. Three features of shells, namely colour, shape and texture were generated from 134 shell species with 10 samples, which were then validated by two different classifiers: k-nearest neighbours (k-NN) and random forest. Since the development of conchology is mature, we believe this dataset can represent a valuable resource for automatic shell recognition. The extracted features of shells are also useful in developing and optimizing new machine learning techniques. Furthermore, we hope more researchers can present new methods to extract shell features and develop new classifiers based on this dataset, in order to improve the recognition performance of shell species.