Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
2,885
datasets available to search
ShareScore release 0.9.0
Dataset results
2,885 results for “Transfers”
FIGURES 6–14. Pteridotelus laticornis White, 1855. 6–10 in Synonymies, transferences, redescriptions and new species in Lamiinae (Coleoptera, Cerambycidae)
FIGURES 6–14. Pteridotelus laticornis White, 1855. 6–10, female: 6, Dorsal habitus; 7, Ventral habitus; 8, Lateral habitus; 9, Head, frontal view; 10, Head and pronotum, dorsal habitus. 11–13, Holotype male of P. hematopus (Lameere, 1884): 11, Dorsal habitus; 12, Lateral habitus; 13, Labels. 14, Dorsal habitus, syntype of P. laticornis.
FIGURES 20–24 in Synonymies, transferences, redescriptions and new species in Lamiinae (Coleoptera, Cerambycidae)
FIGURES 20–24. Acanthoderes (Scythropopsis) pupillata Bates, 1880 comb. nov. 20–23, female: 20, Dorsal habitus; 21, Ventral habitus; 22, Head, frontal view; 23, Lateral habitus. 24, Syntype female, dorsal habitus.
Research data supporting article "Recurrent horizontal transfer identifies mitochondrial positive selection in a transmissible cancer"
<p>Gene expression data supporting analyses described in the article "Recurrent horizontal transfer identifies mitochondrial positive selection in a transmissible cancer" (Strakova et al., 2020).</p>
FIGURES 1–12. 1–7 in Two new species, transference, notes, and new record in South American Acanthocinini (Coleoptera, Cerambycidae, Lamiinae)
FIGURES 1–12. 1–7) Anisopodus flavomarginatus, holotype male: 1) Dorsal habitus; 2) Ventral habitus; 3) Lateral habitus; 4) Head, frontal view; 5) Prothoracic tubercle; 6) Prosternal process; 7) Mesoventral process. 8–11) Anisopodus flavomarginatus, paratype female: 8) Prothoracic tubercle; 9) Prosternal process; 10) Mesoventral process; 11) Dorsal habitus. 12) Anisopodus argus, male, dorsal habitus.
FIGURES 13–17 in Two new species, transference, notes, and new record in South American Acanthocinini (Coleoptera, Cerambycidae, Lamiinae)
FIGURES 13–17. Hylettus eremita, dorsal habitus: 13) Female from Colombia (Boyacá); 14) Male from Colombia (Tolima); 15) Female from Venezuela (Aragua); 16) Male deposited at MNHN (photograph by Jesus Santiago Moure); 17) Holotype male of Hylettus decorticans (photograph by Jesus Santiago Moure).
When and How to Transfer Knowledge in Dynamic Multi-objective Optimization
<p>This file is the output data obtained when running the experiments of the paper below:</p> <p>Ruan, G., Minku, L.L., Menzel, S., Sendhoff, B., Yao, X., "When and How to Transfer Knowledge in Dynamic Multi-objective Optimization," 2019 IEEE Symposium Series on Computational Intelligence (SSCI), Xiamen, China, 2019, pp. 2034-2041. </p> <p> </p> <p>Transfer learning has been used for solving multiple optimization and dynamic multi-objective optimization problems, since transfer learning is able to transfer useful information from one problem to help solving another related problem. This paper aims to investigate when and how transfer learning works or fails in dynamic multi-objective optimization. Through computational analyses on a number of dynamic bi- and tri-objective benchmark problems, we show that transfer learning fails on problems with fixed Pareto optimal solution sets and under small environmental changes. We also show that the Gaussian kernel function used in the existing transfer learning-based method is not always adequate. Therefore, transfer learning should be avoided when dealing with problems for which transfer learning fails and other kernel functions should be used when the Gaussian kernel is inadequate. This paper proposes novel strategies and kernel functions that can be used in such cases. Experimental studies have demonstrated the superiority of our proposed techniques to state-of-the-art methods, on a number of dynamic bi- and tri-objective test problems.</p>
Computational Study on Effectiveness of Knowledge Transfer in Dynamic Multi-objective Optimization
<p>This file is the output data obtained when running the experiments from the paper below:</p> <p>Ruan, G., Minku, L., Menzel, S., Sendhoff, B., Yao., “Computational Study on Effectiveness of Knowledge Transfer in Dynamic Multi-objective Optimization” <em>2020 IEEE Congress on Evolutionary Computation</em></p> <p>Transfer learning has been used for solving multiple optimization and dynamic multi-objective optimization problems, since transfer learning is believed to be able to transfer useful information from one problem instance to help solving another related problem instance. This paper aims to study how effective transfer learning is in dynamic multi-objective optimization (DMO). Through computation time analysis of transfer learning, we show that the ‘inner’ optimization problem introduced by transfer learning is very time-consuming. In order to enhance the efficiency, two alternatives are computationally investigated on a number of dynamic bi- and tri-objective test problems. Experimental results have shown that the greatly enhanced efficiency does not result in much degeneration on the performance of transfer learning. Considering the high computational cost of transfer learning, it is likely that the original purpose of using transfer learning in DMO might be negated. In other words, the computation time saved in optimization is eaten up by computationally expensive transfer learning. As a result, there is less gain than expected in the overall computational efficiency. To verify this, experiments have been conducted, regarding using computational cost of transfer learning to optimize randomly generated solutions. The results have demonstrated that the convergence and diversity of final solutions generated from the random solutions are significantly better than those generated from transferred solutions under the same total computational budget.</p>
Information transfer efficiency differs in wild chimpanzees and bonobos, but not social-cognition
Several theories have been generated to understand the socio-cognitive mechanisms underlying the unique cooperative abilities of humans. The "interdependence hypothesis" posits that the cognitive dimension of human cooperation evolved in contexts when several individuals needed to collaborate to achieve a common goal and that more interdependent individuals are more likely to cooperate (provide services to conspecifics) in non-collaborative contexts. Alternatively, the "social tolerance hypothesis" proposes that higher social tolerance allows conspecifics to cooperate more efficiently and with a wider range of partners. We conducted the first field experimental evaluation of both hypotheses in our closest living relatives by contrasting chimpanzees to the less interdependent but more tolerant bonobos. We compared each species' performance during a non-collaborative cooperative task: informing conspecifics about a danger. We presented Gaboon viper models to 82 individuals from 5 wild communities. Chimpanzees arriving late at the snake were significantly more likely to have heard a call and less likely to startle, indicating that chimpanzees were better informed about the presence of the threat than bonobos. This stems from clear species differences in how individuals adjusted their calling decisions to the level of information already available. Chimpanzees were more likely to call and produced more alarm calls when they had not yet heard a call, whereas bonobos did so when they already heard a call. Our results confirm the link between interdependence and cooperation performance. These species differences were most likely driven by differences in motivation rather than in cognitive capacities since both species tended to consider audience knowledge in their decision to call. Our results inform theories on the evolution of human cooperation by linking inter-group competition pressure and in-group cooperative motivation and/or capability.
GAP model parameter files for "Combining phonon accuracy with high transferability in Gaussian approximation potential models"
<p>GAP model parameter files to accompany the publication</p> <p>"Combining phonon accuracy with high transferability in Gaussian approximation potential models"</p> <p>by Janine George, Geoffroy Hautier, Albert P. Bartók, Gábor Csányi, and Volker L. Deringer</p> <p>All models are defined by the main parameter file "gp_iter6C.xml" and the associated file "gp_iter6C.xml.sparseX.GAP_00001", where "GAP_0000" is a placeholder for the unique identifier of the potential (also given in the XML header), and the trailing "1" indicates that only one set of descriptor (here, SOAP) parameters is given.</p> <p>The directories in this dataset follow the figures in the publication for which the respective potentials have been first used.</p> <p>Fig_2/only_random/M_1000<br> Fig_2/only_random/M_3000<br> Fig_2/only_random/M_5000<br> Fig_2/only_random/M_7000<br> Fig_2/only_random/M_9000</p> <p>Fig_2/only_individual/M_1000<br> Fig_2/only_individual/M_3000<br> Fig_2/only_individual/M_5000<br> Fig_2/only_individual/M_7000<br> Fig_2/only_individual/M_9000</p> <p>Fig_2/combined/M_1000<br> Fig_2/combined/M_3000<br> Fig_2/combined/M_5000<br> Fig_2/combined/M_7000<br> Fig_2/combined/M_9000</p> <p>Fig_4/only_individual/f_0.1000<br> Fig_4/only_individual/f_0.0100<br> Fig_4/only_individual/f_0.0010<br> Fig_4/only_individual/f_0.0001</p> <p>Fig_4/combined/f_0.1000<br> Fig_4/combined/f_0.0100<br> Fig_4/combined/f_0.0010<br> Fig_4/combined/f_0.0001</p> <p>Fig_5/GAP-18_plus_SCs_f0.01 <br> Fig_5/GAP-18_plus_SCs_f0.001</p> <p> </p>
Experimental data for 'The transfer of forces through rough surface contact in concrete'
<p>The data contained in this archive was produced within the research project described in the following thesis:<br> <em>Tirassa M. (2020). The transfer of forces through rough surface contact in concrete. Ph.D. Thesis, EPFL, Lausanne, Switzerland.</em><br> The research project was funded by the Swiss National Science Foundation through research grant 200021_169649.<br> The data relates to the topic of force transfer across concrete cracks and interfaces (rebar-to-concrete) subjected to mixed mode kinematics with constant opening angle. It comprises the measured forces (normal and tangential) and displacements (crack opening and sliding). Moreover, some of the resulting surfaces (scanned using a digital microscope) are included.</p>
Transfer learning enables prediction of CYP2D6 haplotype function
<p>This data here were used to train the models described in the manuscript "Transfer learning enables prediction of CYP2D6 haplotype function". The deep learning model described predicts metabolic function of <em>CYP2D6</em> star alleles. It uses two pretraining steps, first with simulated data, then with sequence data collected from liver microsomes, and finally using sequence data for <em>CYP2D6</em> star alleles.</p> <p> </p> <p>simulated_cyp2d6_diplotypes.tar.gz - This file contains sequence data and labels for simulated <em>CYP2D6 </em>data used in the first training step</p> <p>dalton_2019_cyp2d6_microsomes.txt - This file contains summary statistic data for liver microsome data used in the second pretraining step (originally from <a href="https://doi.org/10.1111/cts.12695">https://doi.org/10.1111/cts.12695)</a></p> <p>star_samples.vcf - This file contains sequence data for <em>CYP2D6 </em>star alleles derived from PharmVar (https://www.pharmvar.org/gene/CYP2D6) used in the final training step.</p>
Data from: De novo gene birth, horizontal gene transfer and gene duplication as sources of new gene families associated with the origin of a symbiosis in Amanita
<p>By introducing novel capacities and functions, new genes and gene families may play a crucial role in ecological transitions. Mechanisms generating new gene families include <i>de novo</i> gene birth, horizontal gene transfer and neofunctionalization following a duplication event. The ectomycorrhizal (ECM) symbiosis is a ubiquitous mutualism and the association has evolved repeatedly and independently many times among the fungi, but the molecular dynamics enabling its emergence remain elusive. We developed a phylogenetic workflow to first understand if gene families unique to ECM <i>Amanita</i> fungi and absent from closely related asymbiotic species are functionally relevant to the symbiosis, and then to systematically infer their origins. We identified 109 gene families unique to ECM <i>Amanita </i>species. Genes belonging to unique gene families are under strong purifying selection and are upregulated during symbiosis, compared to genes of conserved or orphan gene families. The origins of seven of the unique gene families are strongly supported as either <i>de novo</i> gene birth (two gene families), horizontal gene transfer (four), and gene duplication (one). An additional 34 families appear new because of their selective retention within symbiotic species. Among the 109 unique gene families, the most upregulated gene in symbiotic cultures encodes an ACC deaminase, an enzyme capable of downregulating the synthesis of the plant hormone ethylene. Ethylene is a common negative regulator of plant-microbial mutualisms.</p>
Data from: Coral tentacle elasticity promotes an out-of-phase motion that improves mass transfer
Corals rely almost exclusively on the ambient flow of water to support their respiration, photosynthesis, heat exchange, and reproduction. Coral tentacles extend to the flow, interact with it, and oscillate under the influence of waves. Such oscillating motions of flexible appendages are considered adaptive for reducing the drag force on flexible animals in wave-swept environments, but their significance under slower flows is unclear. Using in-situ and laboratory measurements of the motion of coral tentacles under wave-induced flow, we investigated the dynamics of the tentacle motion and its impact on mass transfer. We found that tentacle velocity preceded the water velocity by ~1/4 of a period. This out-of-phase behavior enhanced mass transfer at the tentacle tip by up to 25% as compared with an in-phase motion where drag is minimal. The enhancement was most pronounced under flows slower than 3.2 cm s^-1, which are prevalent in many coral-reef environments. We found that the out-of-phase motion results from the tentacles' elasticity, which can presumably be modified by the animal. Our results suggest that the mechanical properties of coral tentacles, and, may represent an adaptive advantage that improves mass transfer under the limiting conditions of slow ambient flows. Because the mechanism we describe operates by enhancing convective processes, it is expected to enhance other fitness-determining transport phenomena such as heat-exchange and particle capture.
Supplementary material 1 from: Datta A, Schweiger O, Kühn I (2020) Origin of climatic data can determine the transferability of species distribution models. NeoBiota 59: 61-76. https://doi.org/10.3897/neobiota.59.36299
Variable selection using cluster analsys based on Spearman's rank corellation and UPGMA method for agglomeration
Association between seven-day serum β-hCG levels after frozen–thawed embryo transfer and pregnancy outcomes: a single-centre retrospective study from China
<p><span><b><span>Objective:</span></b> Early monitoring of plasma human chorionic gonadotropin (β-hCG) level is vital in predicting pregnancy outcome. This study investigated the predictive value of serum β-hCG level on the 7th day after frozen-thawed embryo transfer (FET) for ongoing pregnancy (OP) and adverse pregnancy (AP). </span></p> <p><span><b><span>Design: </span></b>Retrospective study</span></p> <p><span><b><span>Setting:</span></b> The Reproductive and Genetic Center of the Affiliated Hospital of Shandong University of Traditional Chinese Medicine, China.</span></p> <p><span><b><span>Participants: </span></b>1,061 pregnant women who underwent FET between January 2014 and January 2017. </span></p> <p><span><b><span>Primary and secondary outcome measures: </span></b>Pregnancy outcome.</span></p> <p><span><b><span>Results: </span></b>Serum β-hCG levels on the 7th day after FET were higher in the single OP group compared to the biochemical pregnancy (BP) group (p <0.001). Besides, the serum β-hCG cutoff level at 4.34 mIU/mL on the 7th day showed high predictive value (area under the curve [AUC] = 0.852). Serum β-hCG levels on the 7th day after FET were higher in the twin OP group compared to the single OP group (p<0.001). Also, the serum β-hCG cutoff level at 17.95 mIU/mL on the 7th day showed high predictive value (AUC = 0.903). Serum β-hCG levels on the 7th day after FET were lower in the ectopic pregnancy (EP) group compared to the single OP group (p <0.001) whereas, serum β-hCG cutoff level at 4.53 mIU/mL on the 7th day exhibited a high predictive value (AUC = 0.860). Further, the serum β-hCG levels on the 7th day after FET were lower in the single early spontaneous abortion (SA) group compared to the single OP group (p<0.001) while the serum β-hCG cutoff level at 5.34 mIU/mL on the 7th day exhibited high predictive value (AUC = 0.738).</span></p> <p><span><b><span>Conclusion:</span></b> Serum β-hCG on the 7th day after FET has good clinical significance for the prediction of OP and AP.</span></p>
Resonance energy transfer sensitizes and monitors in situ switching of LOV2-based optogenetic actuators
<p>Engineered light-dependent switches provide uniquely powerful opportunities to investigate and control cell regulatory mechanisms. Existing tools offer high spatiotemporal resolution, reversibility and repeatability. Yet cellular optogenetics applications remain limited in practice. Validation difficulties constrain most usage to easily verified protein translocation rather than inhibition of diffusible targets. Blue light levels commonly needed for actuation can be cytotoxic, precluding long-term experiments. We describe a simple approach overcoming these obstacles. Resonance energy transfer with an adjacent chromophore modulates actuation sensitivity over a 7-fold range. This simultaneously offers on-line monitoring of light-dependent switching and precise quantification of activation-relaxation properties in intact living cells. Applying this approach to different LOV2-based switches reveals relaxation times up to 11-fold faster than anticipated. <em>In situ</em>–measured parameter values guide the design of target-inhibiting actuation trains with minimal blue-light exposure, and context-based optimisation can increase sensitivity and experimental throughput a further 10-fold without loss of temporal precision.</p>
Contact zone of two different chloroplast lineages and genetic guidelines for seed transfer in Quercus serrata and Q. crispula
<p>Within their natural distribution ranges, plant species exhibit genetic structure which has been created by global climate change and natural selection over long periods. To conserve local forests with different genetic structures, genetic guidelines for seed and seedling transfer in individual species are therefore necessary. Genetic guidelines have been published for 43 Japanese tree species using population genetic data; however, for practical use, more detailed genetic borders between important genetic lineages should be clarified to inform seed collection and planting. Thus, we investigated in detail the genetic borders between two important Japanese oak species, Quercus serrata and Q. crispula, in the Chubu region of Japan using chloroplast and nuclear DNA markers, and we discuss the factors that influenced border creation using the results of species distribution modelling (SDM). Two distinct cpDNA haplotypes were found for each species (northern and southern haplotype) within the Chubu region of Japan but the difference in nuclear DNA between northern and southern haplotype populations was very small both in Q. serrata and Q. crispula. The results of SDM showed that during the LGM Q. serrata was distributed mostly along the coastline but Q. crispula was distributed not only along the coast but also in mountainous areas further inland. The cpDNA genetic borders of these two oak species are complex and seem to have been influenced by topography and their distribution during the LGM. We propose and discuss genetic guidelines for these two oak species based on the results of this study.</p>
Calcium stable isotopes of Tonga and Mariana arc lavas and implications for slab fluid-mediated carbonate transfer in subduction zones
<p>The Table 1 shows Ca isotopes and selected major and trace element compositions of the Tonga rear arc and Mariana arc lavas.</p> <p>Supporting imformation includ Figure S1 and Table S1</p> <p>Figure S1 shows the δ<sup>44/42</sup>Ca‰ versus δ<sup>43/42</sup>Ca‰ in all samples and reference materials measured by Nu Plasma 1700 MC-ICP-MS in GPMR.</p> <p>Table S1 lists the major and trace element contents of NW Rota-1 and Esmeralda Bank samples from Mariana arc. Major elements are tested on board and trace elements are measured by ICP-MS in GPMR.</p>
Pollen transfer networks reveal alien species as main heterospecific pollen donors with fitness consequences for natives
<ol> <li>The ecological dynamics of co-flowering communities are largely mediated by pollinators. However, current understanding of pollinator-mediated interactions primarily relies on how co-flowering plants influence attraction of shared pollinators, and much less is known about plan-plant interactions that occur via heterospecific pollen (HP) transfer. Invaded communities in particular can be highly affected by the transfer of alien pollen, but the strength, drivers, and fitness consequences of these interactions at a community scale are not well understood.</li> <li>Here we analyze HP transfer networks in nine coastal communities in the Yucatan Mexico that vary in the relative abundance of invasive flowers to evaluate how HP donation and receipt varies between native and alien plants. We further evaluate whether HP donation and receipt are mediated by floral traits (e.g. display, flower size) or pollinator visitation rate. Finally, we evaluated whether post-pollination success (proportion of pollen tubes produced) was affected by alien HP receipt and whether the effect varied between native and alien recipients.</li> <li>HP transfer networks exhibit relatively high connectance (<i>ca</i>. 15%), suggesting high HP transfer within the studied communities. Significant network nestedness further suggests the existence of species that predominantly act as HP donors or recipients in the community. Species-level analyses showed that natives receive 80% more HP compared to alien species, and that alien plants donate 40% more HP than natives. HP receipt and donation were mediated by different floral traits and such effects were independent of plant origin (native or alien). The proportion of alien HP received significantly affected conspecific pollen tube success in natives, but not that of alien species.</li> <li> <i>Synthesis</i>. Our results suggest that HP transfer in invaded communities is widespread, and that native and alien species play different roles within HP transfer networks, which are mediated by a different suite of floral traits. Alien species, in particular, play a central role as HP donors and are more tolerant to HP receipt than natives—a finding that points to two overlooked mechanisms facilitating alien plant invasion and success within native co-flowering communities.</li> </ol>
Transfer Learning Models and Datasets for a Reliable Emergency Landing Field Identification
<p>The file <em>data.tar.gz</em> compromises three HDF5 datasets. This file has been split into 100 files. The files can be merged, decompressed and unpacked with the following commands:</p> <pre><code class="language-bash">cat data* > data.tar.gz tar -xzf data.tar.gz</code></pre> <p>Afterwards, the three files: <em>train_test_data_ss8_supervised_new.hdf5</em>, <em>train_test_data_ss16_supervised_new.hdf5</em>, <em>train_test_data_ss32_supervised_new.hdf5</em> are ready to get processed. </p> <p>Internal structure of the datasets:<br> <strong>Search Window (SW) 8 m^2:</strong><br> HDF5 "train_test_data_ss8_supervised_new.hdf5" {<br> GROUP "/" {<br> GROUP "test" {<br> DATASET "fus_data" {<br> DATATYPE H5T_IEEE_F32LE<br> DATASPACE SIMPLE { ( 76288, 40, 40, 8 ) / ( 76382, 40, 40, 8 ) }<br> }<br> DATASET "labels" {<br> DATATYPE H5T_STD_I64LE<br> DATASPACE SIMPLE { ( 76382, 1 ) / ( 76382, 1 ) }<br> }<br> }<br> GROUP "train" {<br> DATASET "fus_data" {<br> DATATYPE H5T_IEEE_F32LE<br> DATASPACE SIMPLE { ( 380928, 40, 40, 8 ) / ( 380998, 40, 40, 8 ) }<br> }<br> DATASET "labels" {<br> DATATYPE H5T_STD_I64LE<br> DATASPACE SIMPLE { ( 380998, 1 ) / ( 380998, 1 ) }<br> }<br> }<br> }}</p> <p><br> <strong>SW 16 m^2:</strong><br> HDF5 "train_test_data_ss16_supervised_new.hdf5" {<br> GROUP "/" {<br> GROUP "test" {<br> DATASET "fus_data" {<br> DATATYPE H5T_IEEE_F32LE<br> DATASPACE SIMPLE { ( 17024, 80, 80, 8 ) / ( 17054, 80, 80, 8 ) }<br> }<br> DATASET "labels" {<br> DATATYPE H5T_STD_I64LE<br> DATASPACE SIMPLE { ( 17054, 1 ) / ( 17054, 1 ) }<br> }<br> }<br> GROUP "train" {<br> DATASET "fus_data" {<br> DATATYPE H5T_IEEE_F32LE<br> DATASPACE SIMPLE { ( 84992, 80, 80, 8 ) / ( 85068, 80, 80, 8 ) }<br> }<br> DATASET "labels" {<br> DATATYPE H5T_STD_I64LE<br> DATASPACE SIMPLE { ( 85068, 1 ) / ( 85068, 1 ) }<br> }<br> }<br> }}</p> <p><br> <strong>SW 32 m^2:</strong><br> HDF5 "train_test_data_ss32_supervised_new.hdf5" {<br> GROUP "/" {<br> GROUP "test" {<br> DATASET "fus_data" {<br> DATATYPE H5T_IEEE_F32LE<br> DATASPACE SIMPLE { ( 3328, 160, 160, 8 ) / ( 3359, 160, 160, 8 ) }<br> }<br> DATASET "labels" {<br> DATATYPE H5T_STD_I64LE<br> DATASPACE SIMPLE { ( 3359, 1 ) / ( 3359, 1 ) }<br> }<br> }<br> GROUP "train" {<br> DATASET "fus_data" {<br> DATATYPE H5T_IEEE_F32LE<br> DATASPACE SIMPLE { ( 16768, 160, 160, 8 ) / ( 16793, 160, 160, 8 ) }<br> }<br> DATASET "labels" {<br> DATATYPE H5T_STD_I64LE<br> DATASPACE SIMPLE { ( 16793, 1 ) / ( 16793, 1 ) }<br> }<br> }<br> }}</p> <p>The sample count of the various generated dataset is as follows: <br> <strong>SW 8 m^2:</strong> {train: 380,928 with {0: 190,464, 1: 190,464}, test: 76,288 with {0: 38,152, 1: 38,136}}<br> <strong>SW 16 m^2: </strong>{train: 84,992 with {0: 42,498, 1: 42,494}, test: 17,024 with {0: 8,516, 1: 8,508}}<br> <strong>SW 32 m^2: </strong>{train: 16,768 with {0: 8,424, 1: 8,344}, test: 3,328 with {0: 1,672, 1: 1,656}}</p> <p>Each sample is composed as follows:<br> RGB = sample[:,:,<strong>:3</strong>]; Theoretically: [0, 1] per color channel<br> NIR = sample[:,:,<strong>3</strong>]; Theoretically: [0, 1]<br> Slope = sample[:,:,<strong>4</strong>]; Theoretically: [0, 90]<br> Roughness = sample[:,:,<strong>5</strong>]; Theoretically: [0, 78.78]<br> NDVI = sample[:,:,<strong>6</strong>]; Theoretically: [-1, 1]<br> DOM = sample[:,:,<strong>7</strong>]; Theoretically: [0, 429.90]</p> <p>====================================================================================================</p> <p>The following three files compromise the model and optimizer state variable of our PyTorch models trained on the aforementioned datasets: <em>best_alexnet_final.pth</em>, <em>best_resnet18_final.pth</em>, <em>best_wide_resnet50_2_final.pth</em></p> <p>Below find a more precise description of each model:<br> <strong>best_resnet18_final.pth</strong></p> <ul> <li>Model: ResNet-18</li> <li>Dataset: SW 8</li> <li>Input: RGB-NIR-Slope -> R: [0,224,224], G: [1,224,224], B: [2,224,224], NIR: [3,224,224], Slope: [4,224,224]</li> </ul> <p><strong>best_wide_resnet50_2_final.pth</strong></p> <ul> <li>Model: Wide-ResNet-50-2</li> <li>Dataset: SW 16</li> <li>Input: NDVI-Slope -> NDVI: [0,224,224], Slope: [1,224,224]</li> </ul> <p><strong>best_alexnet_final.pth</strong></p> <ul> <li>Model: AlexNet</li> <li>Dataset: SW 32</li> <li>Input: RGB-Slope -> R: [0,224,224], G: [1,224,224], B: [2,224,224], Slope: [3,224,224]</li> </ul> <p>Each model is capable of performing a binary classification, distinguishing between landable and unlandable samples</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.