Component Retrieval Research Articles

Decomposing Satellite-Based Classification Uncertainties in Large Earth Science Datasets

Collection of increasingly voluminous multispectral data from multiple instruments with high spatial resolution has posed both an opportunity and a challenge for maximizing their utilization, analysis, and impact. Obtaining accurate estimates of precipitation globally with high temporal resolution is crucial for assessing multiscale hydrologic impacts and providing a constraint for development of numerical models of the atmosphere that provide weather and climate predictions. Precipitation type classification plays an important role in constraining both the inverse problem in satellite precipitation retrievals and latent heat transfer within weather prediction simulations. Precipitation type, however, is often reported deterministically, without uncertainty attached to an estimate. Machine learning techniques are capable of extracting content of interest from large datasets and accurately retrieving discrete and continuous properties of physical systems, but with limited insights to the retrieval components—such as errors and the physical relationship between the observed and retrieved properties. To address this shortcoming, we perform precipitation type classification to introduce a novel tool for decomposing errors of satellite-retrieved products. We use Bayesian neural networks to map global precipitation measurement mission microwave imager observations to dual-frequency precipitation radar-derived precipitation type, which perform comparably to deterministic models, but with the added benefit of providing well-calibrated uncertainties. Through uncertainty decomposition, we demonstrate well-calibrated uncertainties as useful for making decisions concerning high uncertainty predictions, model selection, targeted data analysis, and data collection and processing. Additionally, our Bayesian models enable mathematical confirmation of a data distribution change as the cause for an unacceptable decline in model accuracy.

Using temporo-spatial principal component analysis as tool to dissociate latent ERP components of episodic memory retrieval: Objectifying time-window selection for overlapping ERP components

This report details how principal component analysis (PCA) can be used as a valuable tool to dissociate latent ERP components, even when considerable temporal and spatial overlap makes it difficult to discern ERP effects in standard time windows. We illustrate our methodological approach in a data set from a recognition memory paradigm, in which event-related potential (ERP) correlates of familiarity, recollection and the late parietal negativity (LPN) were partially overlapping. By adapting standard time windows based on the results of a temporo-spatial PCA, small yet reliable ERP correlates reflecting familiarity and recollection for identical items and late recollection for changed items were identified, complementing the result pattern observed in behavioral performance. Due to similar temporo-spatial characteristics and opposing polarities in late parietal ERP correlates associated with memory retrieval, component overlap is often observed in this field of research. Hence, the complex interplay of several processes underlying higher cognitive functions such as memory retrieval may interfere with standard ERP assessment. In such instances, PCA can provide promising ways to objectively assess time window selection for subsequent ERP analyses.

Extensive characterization of aerosol optical properties and chemical component concentrations: Application of the GRASP/Component approach to long-term AERONET measurements

A recently developed GRASP/Component approach (GRASP: Generalized Retrieval of Atmosphere and Surface Properties) was applied to AERONET (Aeronet Robotic Network) sun photometer measurements in this study. Unlike traditional aerosol component retrieval, this approach allows the inference of some information about aerosol composition directly from measured radiance, rather than indirectly through the inversion of optical parameters, and has been integrated into the GRASP algorithm. The newly developed GRASP/Component approach was applied to 13 AERONET sites for different aerosol types under the assumption of aerosol internal mixing rules to analyze the characteristics of aerosol components and their distribution patterns. The results indicate that the retrievals can characterize well the spatial and temporal variability of the component concentration for different aerosol types. A reasonable agreement between GRASP BC retrievals and MERRA-2 BC products is found for all different aerosol types. In addition, the relationships between aerosol component content and aerosol optical parameters such as aerosol optical depth (AOD), fine-mode fraction (FMF), absorption Ångström exponent (AAE), scattering Ångström exponent (SAE), and single scattering albedo (SSA) are also analyzed for indirect verifying the reliability of the component retrieval. It was demonstrated the GRASP/Component optical retrievals are in good agreement with AERONET standard products [e.g., correlation coefficient (R) of 0.93–1.0 for AOD, fine-mode AOD (AODF), coarse-mode AOD (AODC) and Ångström exponent (AE); R = ~ 0.8 for absorption AOD (AAOD) and SSA; RMSE (root mean square error) < 0.03 for AOD, AODF, AODC, AAOD and SSA]. Thus, it is demonstrated the GRASP/Component approach can provide aerosol optical products with comparable accuracy as the AERONET standard products from the ground-based sun photometer measurements as well as some additional important inside on aerosol composition.

A satellite-measured view of aerosol component content and optical property in a haze-polluted case over North China Plain

The Directional Polarimetric Camera (DPC) is the first Chinese satellite-borne multi-angle polarimetric sensor onboard the GaoFen-5 (GF-5) satellite, which was launched on May 9th 2018. In this paper, we present the spatiotemporal variability of satellite-measured aerosol components (such as, black carbon, brown carbon, iron oxides contained in mineral dust etc.) over North China Plain (36–41°N, 113–123°E) for a heavily haze-polluted case, to demonstrate the first successful retrievals of aerosol component content and optical property directly from the DPC/GF-5 instrument measurements. We also reveal the relationship between absorbing/scattering component mass ratio and aerosol absorption based on the multi-angle polarimetric satellite measurements, which presents comparable agreement with previous laboratory studies and field studies for an indirect validation of aerosol component retrievals. In addition, the feasibility, stability and uncertainty of the aerosol optical property and component content retrievals from DPC multi-angle polarimetric observations were evaluated and assessed by sensitivity tests. The distributions of DPC/GF-5 aerosol optical depth (AOD) are in line with satellite-observed MODIS (Moderate-resolution Imaging Spectroradiometer) AOD and ground-based CARSNET (China Aerosol Remote Sensing Network) AOD products. Therefore, the multi-angle polarimetric satellite measurements show an encouraging potential for the comprehensive inversion of aerosol optical, microphysical and chemical properties. The results and further applications of this component algorithm in the future are helpful to reduce the uncertainty of climate change assessment by providing the measurements of aerosol component, in particular for black carbon, brown carbon, and iron oxides contained in dust, with large and extensive spatiotemporal scale.

Columnar aerosol types and compositions over peninsular Southeast Asia based on long-term AERONET data

Aerosol chemical components such as black carbon (BC) and brown carbon (BrC) regulate aerosol optical properties, which in turn drive the atmospheric radiative forcing estimations due to aerosols. In this study, we used the long-term measurements from AERONET (Aerosol Robotic Network) to better understand the aerosol types and composition with respect to their seasonal and spatial variabilities in peninsular Southeast Asia (PSEA, here defined as Vietnam, Cambodia, Thailand, Laos, and Myanmar). Two methods (i.e., aerosol type cluster and aerosol component retrieval) were applied to determine the aerosol type and chemical composition during the biomass-burning (BB) season. AERONET sites in northern PSEA showed a higher AOD (aerosol optical depth) compared to that of southern PSEA. Differences in land use pattern, geographic location, and weather regime caused much of the aerosol variability over PSEA. Lower single-scattering albedo (SSA) and higher fine-mode fraction (FMF) values were observed in February and March, suggesting the predominance of BB type aerosols with finer and stronger absorbing particles during the dry season. However, we also found that the peak BB month (i.e., March) in northern PSEA may not coincide with the lowest SSA once dust particles have mixed with the other aerosols. Furthermore, we investigated two severe BB events in March of 2014 and 2015, revealing a significant BrC fraction during BB event days. On high AOD days, although the BC fraction was high, the BrC fraction remained low due to lack of aerosol aging. This study highlights the dominance of carbonaceous aerosols in the PSEA atmosphere during the BB season, while also revealing that transported dust particles and BrC aerosol aging may introduce uncertainties into the aerosol radiative forcing calculation.

A Review on Fact Extraction and Verification

We study the fact-checking problem, which aims to identify the veracity of a given claim. Specifically, we focus on the task of Fact Extraction and VERification (FEVER) and its accompanied dataset. The task consists of the subtasks of retrieving the relevant documents (and sentences) from Wikipedia and validating whether the information in the documents supports or refutes a given claim. This task is essential and can be the building block of applications such as fake news detection and medical claim verification. In this article, we aim at a better understanding of the challenges of the task by presenting the literature in a structured and comprehensive way. We describe the proposed methods by analyzing the technical perspectives of the different approaches and discussing the performance results on the FEVER dataset, which is the most well-studied and formally structured dataset on the fact extraction and verification task. We also conduct the largest experimental study to date on identifying beneficial loss functions for the sentence retrieval component. Our analysis indicates that sampling negative sentences is important for improving the performance and decreasing the computational complexity. Finally, we describe open issues and future challenges, and we motivate future research in the task.

Reusable Component Retrieval from a Large Repository Using Word2Vec with Continuous Bag of Words

A reusable code component is the one which can be easily used with a little or no adaptation to fit in to the application being developed. The major concern in such process is the maintenance of these reusable components in one place called ‘Repository’, so that those code components can be effectively identified as well as reused. Word embedding allows us to numerically represent our textual information. They have become so pervasive that almost all Natural Language Processing projects make use of them. In this work, we considered to use Word2Vec concept to find vector representation of features of a reusable component. The features of a reusable component in the form of sequence of words are input to Word2Vec network. Our method using Word2Vec with Continuous Bag of Words out performs existing method in the market. The proposed methodology has shown an accuracy of 94.8% in identifying the existing reusable component.

Evaluation of Remote-Sensing Reflectance Products from Multiple Ocean Color Missions in Highly Turbid Water (Hangzhou Bay)

Validation of remote-sensing reflectance (Rrs) products is necessary for the quantitative application of ocean color satellite data. While validation of Rrs products has been performed in low to moderate turbidity waters, their performance in highly turbid water remains poorly known. Here, we used in situ Rrs data from Hangzhou Bay (HZB), one of the world’s most turbid estuaries, to evaluate agency-distributed Rrs products for multiple ocean color sensors, including the Geostationary Ocean Color Imager (GOCI), Chinese Ocean Color and Temperature Scanner aboard HaiYang-1C (COCTS/HY1C), Ocean and Land Color Instrument aboard Sentinel-3A and Sentinel-3B, respectively (OLCI/S3A and OLCI/S3B), Second-Generation Global Imager aboard Global Change Observation Mission-Climate (SGLI/GCOM-C), and Visible Infrared Imaging Radiometer Suite aboard the Suomi National Polar-orbiting Partnership satellite (VIIRS/SNPP). Results showed that GOCI and SGLI/GCOM-C had almost no effective Rrs products in the HZB. Among the others four sensors (COCTS/HY1C, OLCI/S3A, OLCI/S3B, and VIIRS/SNPP), VIIRS/SNPP obtained the largest correlation coefficient (R) with a value of 0.7, while OLCI/S3A obtained the best mean percentage differences (PD) with a value of −13.30%. The average absolute percentage difference (APD) values of the four remote sensors are close, all around 45%. In situ Rrs data from the AERONET-OC ARIAKE site were also used to evaluate the satellite-derived Rrs products in moderately turbid coastal water for comparison. Compared with the validation results at HZB, the performances of Rrs from GOCI, OLCI/S3A, OLCI/S3B, and VIIRS/SNPP were much better at the ARIAKE site with the smallest R (0.77) and largest APD (35.38%) for GOCI, and the worst PD for these four sensors was only −13.15%, indicating that the satellite-retrieved Rrs exhibited better performance. In contrast, Rrs from COCTS/HY1C and SGLI/GCOM-C at ARIAKE site was still significantly underestimated, and the R values of the two satellites were not greater than 0.7, and the APD values were greater than 50%. Therefore, the performance of satellite Rrs products degrades significantly in highly turbid waters and needs to be improved for further retrieval of ocean color components.

Web-based Application Forecasting of Components and Tools for Practicum in Telecommunication Engineering Laboratory/ Workshop of State Polytechnic of Sriwijaya

State Polytechnic of Sriwijaya is an Indonesian vocational institution that incorporates practical learning into all of its existing study programs. In each laboratory of the study program, students will find the supporting components and resources they need for practicum. Telecommunication engineering is one of them. Currently, the component retrieval and tool borrowing system is still manual, both in the retrieval and return stages, by filling out the given hard-file form sheet. Therefore, a web-based inventory monitoring application is required for laboratory technicians. The creation of this application implements the Prototype Method. The implementation of this method aims to make the application that is created to fit the needs of the user. This system helps laboratory technicians and Telecommunication Engineering students in the process of component retrieval and tool borrowing to be more organized and scheduled and can store reports in the form of soft-files. This information system can also be used by students to monitor the number of components and tools available in real-time. This application are also equipped with forecasting the number of practicum components to kwowing the needs of student practicum in the next year. Forecasting was created using the Weighted Moving Average method. Black box testing is carried out in each menu on the application and gives valid results so that the application can be used.

Valorization of toxic discarded fish skin for biomedical application

Fish discards are dumped into the sea and sea shore during fishing and segregation by fishing sectors. Fish of no or low economic value, or damaged and of a reduced value are thrown away. The discards adversely affect the marine habitats and huge number of proteins, essential fatty acids, collagen, enzymes are lost. The retrieval of the value-added components from these discards will be a better approach for waste utilization and for a cleaner ecosystem. The purpose of this study is to maximize the output and minimize the waste. As pollution generation is related to an inefficiency of resource use, the present study describes the state-of-the-art to make use of a discarded fish, Trachicephalus uranoscopus, for extracting collagen. High yield of 58.3% collagen was obtained through pepsin extraction and sodium dodecyl sulfate polyacrylamide gel electrophoresis revealed that the isolated collagen was type I. The collagen was crosslinked with chemical crosslinkers and formed as a scaffold. The scaffold exhibited a maximum crosslinking efficiency of 60.92% and was stable for about 72 h with 50% enzymatic degradation rate. The whole blood clotting experiment and RBC attachment indicated hemocompatibility of the scaffolds. In vitro cytotoxic study in 3T3 fibroblast cells exhibited cell viability of 100% showing biocompatibility of the prepared scaffolds. From the results it can be concluded that the extracted collagen could be used for biomedical applications as an alternate for bovine collagen. The value-added product from the discarded fish skin has a positive impact on the marine ecosystem, human health, and the development of fishing industries.

On the Geo-Indicativeness of Non-Georeferenced Text

Geographic location is a key component for information retrieval on the Web, recommendation systems in mobile computing and social networks, and place-based integration on the Linked Data cloud. Previous work has addressed how to estimate locations by named entity recognition, from images, and via structured data. In this paper, we estimate geographic regions from unstructured, non geo-referenced text by computing a probability distribution over the Earth's surface. Our methodology combines natural language processing, geostatistics, and a data-driven bottom-up semantics. We illustrate its potential for mapping geographic regions from non geo-referenced text.

Measuring corner cube reflectors through ray tracing of a reflected wavefront.

The corner cube plays a key role in many advanced optical systems as the critical retrieval component, while the errors such as dihedral deviation will lead to unacceptable results. We present a method to obtain the right-angle plane deviation of the corner cube only by measuring and calculating the normal incident reflection wavefront. The calculation process is an iterative method of ray tracing based on the corner cube reflection process. The three-dimensional shape of the right-angle plane of the corner cube can be obtained accurately by this method. The proposed method is easy to implement and reliable, and it avoids the complicated operation of the traditional measurement method, which can also be applied to the measurement of the errors in the assembly and adjustment process where corner cube reflectors are used.

Feature Re-Learning for Video Recommendation

Predicting the relevance between two given videos with respect to their visual content is a key component for content-based video recommendation and retrieval. The application is in video recommendation, video annotation, Category or near-duplicate video retrieval, video copy detection and so on. In order to estimate video relevance previous works utilize textual content of videos and lead to poor performance. The proposed method is feature re-learning for video relevance prediction. This work focus on the visual contents to predict the relevance between two videos. A given feature is projected into a new space by an affine transformation. Different from previous works this use a standard triplet ranking loss that optimize the projection process by a novel negative-enhanced triplet ranking loss. In order to generate more training data, propose a data augmentation strategy which works directly on video features. The multi-level augmentation strategy works for video features, which benefits the feature relearning. The proposed augmentation strategy can be flexibly used for frame-level or video-level features. The loss function that consider the absolute similarity of positive pairs and supervise the feature re-learning process and a new formula for video relevance computation.

The Effect of Principal Component Analysis Parameters on Solar-Induced Chlorophyll Fluorescence Signal Extraction

Solar-induced chlorophyll fluorescence (SIF), one of the three main releasing pathways of vegetation-absorbed photosynthetic active radiation, has been proven as an effective monitoring implementation of leaf photosynthesis, canopy growth, and ecological diversity. There exist three categories of SIF retrieval methods, and the principal component analysis (PCA) retrieval method is obtrusively eye-catching due to its brief, data-driven characteristics. However, we still lack a lucid understanding of PCA’s parameter settings. In this study, we examined if principal component numbers and retrieval band regions could have effects on the accuracy of SIF inversion under two controlled experiments. The results revealed that the near-infrared region could remarkably boost SIF’s retrieval accuracy, whereas red and near-infrared bands caused anomalous values, which subverted a traditional view that more retrieval regions might provide more photosynthetic information. Furthermore, the results demonstrated that three principal components would benefit more in PCA-based SIF retrieval. These arguments further help elucidate the more in-depth influence of the parameters on the PCA retrieval method, which unveil the potential effects of different parameters and give a parameter-setting foundation for the PCA retrieval method, in addition to assisting retrieval achievements.

ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces

As mobile devices are becoming ubiquitous, regularly interacting with a variety of user interfaces (UIs) is a common aspect of daily life for many people. To improve the accessibility of these devices and to enable their usage in a variety of settings, building models that can assist users and accomplish tasks through the UI is vitally important. However, there are several challenges to achieve this. First, UI components of similar appearance can have different functionalities, making understanding their function more important than just analyzing their appearance. Second, domain-specific features like Document Object Model (DOM) in web pages and View Hierarchy (VH) in mobile applications provide important signals about the semantics of UI elements, but these features are not in a natural language format. Third, owing to a large diversity in UIs and absence of standard DOM or VH representations, building a UI understanding model with high coverage requires large amounts of training data. Inspired by the success of pre-training based approaches in NLP for tackling a variety of problems in a data-efficient way, we introduce a new pre-trained UI representation model called ActionBert. Our methodology is designed to leverage visual, linguistic and domain-specific features in user interaction traces to pre-train generic feature representations of UIs and their components. Our key intuition is that user actions, e.g., a sequence of clicks on different UI components, reveals important information about their functionality. We evaluate the proposed model on a wide variety of downstream tasks, ranging from icon classification to UI component retrieval based on its natural language description. Experiments show that the proposed ActionBert model outperforms multi-modal baselines across all downstream tasks by up to 15.5%.

Neuroplastic effects of a selective serotonin reuptake inhibitor in relearning and retrieval

Animal studies using selective serotonin reuptake inhibitors (SSRIs) and learning paradigms have demonstrated that serotonin is important for flexibility in executive functions and learning. SSRIs might facilitate relearning through neuroplastic processes and thus exert their clinical effects in psychiatric diseases where cognitive functioning is affected. However, translation of these mechanisms to humans is missing. In this randomized placebo-controlled trial, we assessed functional brain activation during learning and memory retrieval in healthy volunteers performing associative learning tasks aiming to translate facilitated relearning by SSRIs.To this extent, seventy-six participants underwent three MRI scanning sessions: (1) at baseline, (2) after three weeks of daily associative learning and subsequent retrieval (face-matching or Chinese character–noun matching) and (3) after three weeks of relearning under escitalopram (10 mg/day) or placebo. Associative learning and retrieval tasks were performed during each functional MRI (fMRI) session. Statistical modeling was done using a repeated-measures ANOVA, to test for content-by-treatment-by-time interaction effects.During the learning task, a significant substance-by-time interaction was found in the right insula showing a greater deactivation in the SSRI cohort after 21 days of relearning compared to the learning phase. In the retrieval task, there was a significant content-by-time interaction in the left angular gyrus (AG) with an increased activation in face-matching compared to Chinese-character matching for both learning and relearning phases. A further substance-by-time interaction was found in task performance after 21 days of relearning, indicating a greater decrease of performance in the placebo group.Our findings that escitalopram modulate insula activation demonstrates successful translation of relearning as a mechanism of SSRIs in human. Furthermore, we show that the left AG is an active component of correct memory retrieval, which coincides with previous literature. We extend the function of this region by demonstrating its activation is not only stimulus dependent but also time constrained. Finally, we were able to show that escitalopram aids in relearning, irrespective of content.

Retrieval of software components using NLP based IR model

Software engineering is one of the traditional domains that integrates and updates its techniques with all the novel methodologies time to time. There are different process models to develop software and CBD (Component Based Development) is one among them. CBD is an agile model that uses a component to develop the software instead of doing it from scratch. The component used in the proposed work is a piece of code.This paper explains a component based software reuse based on the NLP (Natural language processing) based IR (Information retrieval) technique.

Evaluation of regions suitable for vicarious calibration of ocean color satellite sensors in the South China Sea.

Accurate retrieval of biogeochemical components of the ocean at a global scale from space requires accurately calibrated top-of-atmosphere (TOA) radiance, which is usually achieved by deriving a vicarious gain coefficient (g-factor) through a process called system vicarious calibration (SVC). Currently, only two SVC sites, Marine Optical Buoy (MOBY) and BOUée pour l'acquiSition d'une Série Optique à Long termE (BOUSSOLE), are routinely operated to support the SVC process for all on-orbit ocean color satellite payloads. However, high-quality matchups between satellite observations and in situ measurements are rare because of the strict requirements of the SVC process. Meanwhile, a stable g-factor is usually computed by averaging sufficient gain measurements. Therefore, more SVC sites are required to derive a stable g-factor in a short duration, particularly for the initial calibration of newly launched satellite sensors. In this study, nearly twenty years of well-calibrated ocean color satellite data were used to calculate the mean and standard deviation of physical and optical properties of waters and the atmosphere in the South China Sea (SCS) to evaluate the feasibility of establishing a SVC site. A region was identified that meets all requirements that were used to evaluate the MOBY and BOUSSOLE sites. Two in situ measurements within this region were used to derive a g-factor for MODIS-Terra and MODIS-Aqua and were compared with the g-factor derived using MOBY data. The consistence of the two g-factors indicates that the identified region in the SCS could be a potential area for establishing a long-term moored SVC site.

Latency‐based functional analysis and treatment of elopement

AbstractAlthough functional analysis (FA) methodology has been used to identify treatments for elopement, the results of some of these analyses have been confounded by the retrieval of participants. Recently, researchers have used latency‐based FAs, which eliminate the retrieval component during a session, to assess elopement. In the current study, we replicated previous research using latency‐based FAs to assess elopement exhibited by three children with autism. In addition, we evaluated function‐based treatments for each participant. The treatments effectively decreased elopement for all participants, partially validating the latency‐based FAs.

Event Geoparser with Pseudo-Location Entity Identification and Numerical Argument Extraction Implementation and Evaluation in Indonesian News Domain

Geoparser is a fundamental component of a Geographic Information Retrieval (GIR) geoparser, which performs toponym recognition, disambiguation, and geographic coordinate resolution from unstructured text domain. However, geoparsing of news articles which report several events across many place-mentions in the document are not yet adequately handled by regular geoparser, where the scope of resolution is either toponym-level or document-level. The capacity to detect multiple events and geolocate their true coordinates along with their numerical arguments is still missing from modern geoparsers, much less in Indonesian news corpora domain. We propose an event geoparser model with three stages of processing, which tightly integrates event extraction model into geoparsing and provides precise event-level resolution scope. The model casts the geotagging and event extraction as sequence labeling and uses LSTM-CRF inferencer equipped with features derived using Aggregated Topic Model from a large corpus to increase the generalizability. Throughout the proposed workflow and features, the geoparser is able to significantly improve the identification of pseudo-location entities, resulting in a 23.43% increase for weighted F1 score compared to baseline gazetteer and POS Tag features. As a side effect of event extraction, various numerical arguments are also extracted, and the output is easily projected to a rich choropleth map from a single news document.