Accuracy Of Dataset Research Articles

Optimization of a Wireless Sensor Network‐Based Smart Elderly Location Management System

In this paper, wireless sensors are used to design and build a location management system for smart aging, and the optimization of this system is analysed. The function and structure of the positioning system are designed and implemented. Next, the system commissioning process and field implementation results are summarized and analysed to guarantee the reliability and integrity of the system. Finally, the system requirements and implementation are integrated to realize the basic requirements of the IoT‐based elderly positioning management system and reserve the interface for later expansion. Finally, the system excellence and functional usability tested through unit testing as well as comprehensive testing. In this paper, a theoretical analysis of the prediction algorithm is carried out for the disease prediction module in the health monitoring software of the smart senior care system. To improve the accuracy of the prediction, the traditional BP neural network algorithm is optimized using DS evidence theory, thus fusing multiple sets of prediction results obtained from the BP neural network into a more accurate set of data, and the performance of the algorithm before and after the improvement is compared. The IoT‐based home health management for the elderly starts from the health service demand of the elderly, explains the basic concept of IoT technology and home health management for the elderly, and analyses the feasibility of home health management for the elderly and the advantages of IoT technology in‐home health management for the elderly; through the field research, the IoT‐based home health management platform for the elderly is carried out from three aspects of users, business, and technology. The design covers the platform architecture and functional modules of the IoT‐based senior home health management platform, which can solve the problem that the elderly can spend a comfortable life in their old age without going home.

Migration in the national context - mapping the research challenges

Contemporary migration is characterized by its very dynamic nature. In that sense, it is extremely important that scientific knowledge, academic research, as well as the public policy measures, be based on current research and accurate data sets. Furthermore, theoretical papers explaining relevant phenomena and concepts could be equally relevant and useful like the empirical ones, putting more light on the specific problems in the process of creating and implementing public policies. The purpose of this paper is to emphasize the links between the topics in scientific papers and policymakers? needs through the desk analysis of the leading Serbian national scientific journals in the areas of social sciences and humanities. The analysis of 41 papers in total was related to the identification of three specific migration topics: migration and development, integration and migration governance. Through comparison between the global research trends and the national approaches and findings certain conclusions were drawn and recommendations were given. Detailed analysis led to findings that some of the selected academic research could be a reliable and useful source for the decision makers. This is a necessary step for development of efficient and timely state responses to existing and future challenges brought by migration.

Hybrid Particle Filter Trained Neural Network for Prognosis of Lithium-Ion Batteries

Prognostics and Health Management (PHM) plays a key role in Industry 4.0 revolution by providing smart predictive maintenance solutions. Early failure detection and prediction of remaining useful life (RUL) of critical industrial machines/components are the main challenges addressed by PHM methodologies. In literature, model-based and data-driven methods are widely used for RUL estimation. Model-based methods rely on empirical/phenomenological degradation models for RUL prediction using Bayesian formulations. In many cases, the lack of accurate physics-based models emphasizes the need to resort to machine learning based prognostic algorithms. However, data-driven methods require extensive machine failure data incorporating all possible operating conditions along with all possible failure modes pertaining to that particular machine/component, which are seldom available in their entirety. In this work, we propose a three-stage hybrid prognostic algorithm (HyA) combining model-based (Particle Filters-PF) and data-driven (Neural Networks-NN) methods in a unique way. The proposed method aims to overcome the need for accurate degradation modeling or extensive failure data sets. In the first stage, a feedforward neural network is used to formulate lithium-ion battery’s degradation trends and the corresponding NN model parameters are used to define the initial prior distribution of PF algorithm. In the second stage, the PF algorithm optimizes the model parameters and the posterior model parameter distributions are utilized to ‘ warm-start ’ the neural network used for prognosis and the third/final stages focuses on prognosis and RUL estimation using the trained NN model leveraging on the posterior distributions of the PF fine-tuned weights and biases. The proposed method is demonstrated on CALCE and NASA lithium-ion battery capacity degradation datasets. The efficacy of the proposed hybrid algorithm is evaluated using root mean square error (RMSE) values and alpha-lambda prognostic metrics. Also, the impact of the NN architecture on the prediction accuracy and computational load are analyzed.

Efficient detection of hacker community based on twitter data using complex networks and machine learning algorithm

Twitter is one of the most popular platforms used to share and post ideas. Hackers and anonymous attackers use these platforms maliciously, and their behavior can be used to predict the risk of future attacks, by gathering and classifying hackers’ tweets using machine-learning techniques. Previous approaches for detecting infected tweets are based on human efforts or text analysis, thus they are limited to capturing the hidden text between tweet lines. The main aim of this research paper is to enhance the efficiency of hacker detection for the Twitter platform using the complex networks technique with adapted machine learning algorithms. This work presents a methodology that collects a list of users with their followers who are sharing their posts that have similar interests from a hackers’ community on Twitter. The list is built based on a set of suggested keywords that are the commonly used terms by hackers in their tweets. After that, a complex network is generated for all users to find relations among them in terms of network centrality, closeness, and betweenness. After extracting these values, a dataset of the most influential users in the hacker community is assembled. Subsequently, tweets belonging to users in the extracted dataset are gathered and classified into positive and negative classes. The output of this process is utilized with a machine learning process by applying different algorithms. This research build and investigate an accurate dataset containing real users who belong to a hackers’ community. Correctly, classified instances were measured for accuracy using the average values of K-nearest neighbor, Naive Bayes, Random Tree, and the support vector machine techniques, demonstrating about 90% and 88% accuracy for cross-validation and percentage split respectively. Consequently, the proposed network cyber Twitter model is able to detect hackers, and determine if tweets pose a risk to future institutions and individuals to provide early warning of possible attacks.

Enhancement Performance of Multiple Objects Detection and Tracking for Real-time and Online Applications

Multi-object detection and tracking systems represent one of the basic and important tasks of surveillance and video traffic systems. Recently. The proposed tracking algorithms focused on the detection mechanism. It showed significant improvement in performance in the field of computer vision. Though. It faced many challenges and problems, such as many blockages and segmentation of paths, in addition to the increasing number of identification keys and false-positive paths. In this work, an algorithm was proposed that integrates information on appearance and visibility features to improve the tracker's performance. It enables us to track multiple objects throughout the video and for a longer period of clogging and buffer a number of ID switches. An effective and accurate data set, tools, and metrics were also used to measure the efficiency of the proposed algorithm. The experimental results show the great improvement in the performance of the tracker, with high accuracy of more than 65%, which achieves competitive performance with the existing algorithms.

Developing Crowdsourced Training Data Sets for Pharmacovigilance Intelligent Automation.

Machine learning offers an alluring solution to developing automated approaches to the increasing individual case safety report burden being placed upon pharmacovigilance. Leveraging crowdsourcing to annotate unstructured data may provide accurate, efficient, and contemporaneous training data sets in support of machine learning. The objective of this study was to evaluate whether crowdsourcing can be used to accurately and efficiently develop training data sets in support of pharmacovigilance automation. Pharmacovigilance experts created a reference dataset by reviewing 15,490 de-identified social media posts of narratives pertaining to 15 drugs and 22 medically relevant topics. A random sampling of posts from the reference dataset was published on Amazon Turk and its users (Turkers) were asked a series of questions about those same medical concepts. Accuracy, price elasticity, and time efficiency were evaluated. Accuracy of crowdsourced curation exceeded 90% when compared to the reference dataset and was completed in about 5% of the time. There was an increase in time efficiency with higher pay, but there was no significant difference in accuracy. Additionally, having a social media post reviewed by more than one Turker (using a voting system) did not offer significant improvements in terms of accuracy. Crowdsourcing is an accurate and efficient method that can be used to develop training data sets in support of pharmacovigilance automation. More research is needed to better understand the breadth and depth of possible uses as well as strengths, limitations, and generalizability of results.

VisionBlender: a tool to efficiently generate computer vision datasets for robotic surgery

ABSTRACT Surgical robots rely on robust and efficient computer vision algorithms to be able to intervene in real-time. The main problem, however, is that the training or testing of such algorithms, especially when using deep learning techniques, requires large endoscopic datasets which are challenging to obtain, since they require expensive hardware, ethical approvals, patient consent and access to hospitals. This paper presents VisionBlender, a solution to efficiently generate large and accurate endoscopic datasets for validating surgical vision algorithms. VisionBlender is a synthetic dataset generator that adds a user interface to Blender, allowing users to generate realistic video sequences with ground truth maps of depth, disparity, segmentation masks, surface normals, optical flow, object pose, and camera parameters. VisionBlender was built with special focus on robotic surgery, and examples of endoscopic data that can be generated using this tool are presented. Possible applications are also discussed, and here we present one of those applications where the generated data has been used to train and evaluate state-of-the-art 3D reconstruction algorithms. Being able to generate realistic endoscopic datasets efficiently, VisionBlender promises an exciting step forward in robotic surgery.

Big LIDAR Data in Digital Earth: Ways Out of Dead End

During past 25 years, laser scanning has evolved from an experimental method into a fully autonomous family of Earth remote sensing methods. Now this group of methods provides the most accurate and detailed spatial data sets, while the cost of data is constantly falling, the number of measuring instruments (laser scanners) is constantly growing. The volumes of data that will be obtained during the surveys in the coming decades will allow the creation of the first sub-global coverage of the planet. However, the flip side of high accuracy and detail is the need to store fantastically large volumes of three-dimensional data without loss of accuracy. At the same time, the ability to work with the specified data in both 2D and 3D mode should be improved. Standard storage methods (file method, geodatabases, archiving, etc) solve the problem only partially. At the same time, there are some other alternative methods that can remove current restrictions and lead to the emergence of more flexible and functional spatial data infrastructures. One of the most flexible and promising ways of laser data storage and processing are quadtree and octree-based approaches. Of course, these approaches are more complicated than typical file data structures, that are commonly used for LIDAR data storage, but they allow users to solve some typical negative features of point datasets (processing speed, non-topological spatial structure, limited precision, etc.).

About the Pitfall of Erroneous Validation Data in the Estimation of Confusion Matrices

Accuracy assessment of maps relies on the collection of validation data, i.e., a set of trusted points or spatial objects collected independently from the classified map. However, collecting spatially and thematically accurate dataset is often tedious and expensive. Despite good practices, those datasets are rarely error-prone. Errors in the reference dataset propagate to the probabilities estimated in the confusion matrices. Consequently, the estimates of the quality are biased: accuracy indices are overestimated if the errors are correlated and underestimated if the errors are conditionally independent. The first findings of our study highlight the fact that this bias could invalidate statistical tests of map accuracy assessment. Furthermore, correlated errors in the reference dataset induce unfair comparison of classifiers. A maximum entropy method is thus proposed to mitigate the propagation of errors from imperfect reference datasets. The proposed method is based on a theoretical framework which considers a trivariate probability table that links the observed confusion matrix, the confusion matrix of the reference dataset and the “real” confusion matrix. The method was tested with simulated thematic and geo-reference errors. It proved to reduce the bias to the level of the sampling uncertainty. The method was very efficient with geolocation errors because conditional independence of errors can reasonably be assumed. Thematic errors are more difficult to mitigate because they require the estimation of an additional parameter related to the amount of spatial correlation. In any case, while collecting additional trusted labels is usually expensive, our result show that the benefits for accuracy assessment are much larger than collecting a larger number of questionable reference data.

Investigating surface condition classification of flexible road pavement using data mining techniques

ABSTRACT The lack of sufficient, accurate and time series dataset on road pavement surface condition in most developing countries over time has posed a serious challenge to highway engineers in terms of developing reliable pavement management system. This study examined the trend of flexible road pavement behaviour and surface condition classification from a historic dataset using intelligent algorithms such as; Random Forest (RF), Decision Tree (DT) and Naïve Bayes (NB) theory implemented in the Waikato Environment for Knowledge Analysis (WEKA) software. Some randomly selected highway links were considered for the investigation. The surface condition attributes considered included the percentage of fatigue cracks, average rut depth and drainage condition in a relatively comprehensive database obtained from the Federal Ministry of Power, Works and Housing Nigeria. Results of the analysis revealed the performance trend and classification of road pavement surface conditions based on surface distresses. The analysis indicated that, the RF and DT algorithms yielded accurate classification against the NB algorithm which could not handle instances of missing data efficiently, hence incurred classification errors. The use of experience-based models that could handle challenges of missing data in a dataset was recommended for the development of road pavement management system using such database.

The content and accuracy of the CORINE Land Cover dataset for Norway

The CORINE Land Cover dataset for Norway for the reference year 2018 (CLC2018) was compared to detailed national land cover and land use data. This allowed us to describe the thematic composition of the CLC-polygons and aggregate the information into statistical profiles for each CLC-class. We compared the results to the class definitions found in the CLC mapping instructions, while considering the generalization and minimal mapping units required for CLC. The study showed that CLC2018 in general complied with the definitions. Nonconformities were mainly found for detailed and (in a Norwegian context) marginal classes. The classification can still be improved by complementing visual interpretation with classification based on the statistical profile of each polygon when detailed land use and land cover information is available. The use of auxiliary information at the polygon level can thus provide a better, thematically more accurate CLC dataset for use in European land monitoring.

Assessing the Impact of Land Use and Land Cover Data Representation on Weather Forecast Quality: A Case Study in Central Mexico

In atmospheric modeling, an accurate representation of land cover is required because such information impacts water and energy budgets and, consequently, the performance of models in simulating regional climate. This study analyzes the impact of the land cover data on an operational weather forecasting system using the Weather Research and Forecasting (WRF) model for central Mexico, with the aim of improving the quality of the operative forecast. Two experiments were conducted using different land cover datasets: a United States Geological Survey (USGS) map and an updated North American Land Change Monitoring System (NALCMS) map. The experiments were conducted as a daily 120 h forecast for each day of January, April, July, and September of 2012, and the near-surface temperature, wind speed, and hourly precipitation were analyzed. Both experiments were compared with observations from meteorological stations. The statistical analysis of this study showed that wind speed and near-surface temperature prediction may be further improved with the updated and more accurate NALCMS dataset, particularly in the forecast covering 48 to 72 h. The Root Mean Square Error (RMSE) of the average wind speed reached a maximum reduction of up to 1.2 m s−1, whereas for the near-surface temperature there was a reduction of up to 0.6 °C. The RMSE of the average hourly precipitation was very similar between both experiments, however the location of precipitation was modified.

Highly accurate long-read HiFi sequencing data for five complex genomes

The PacBio® HiFi sequencing method yields highly accurate long-read sequencing datasets with read lengths averaging 10–25 kb and accuracies greater than 99.5%. These accurate long reads can be used to improve results for complex applications such as single nucleotide and structural variant detection, genome assembly, assembly of difficult polyploid or highly repetitive genomes, and assembly of metagenomes. Currently, there is a need for sample data sets to both evaluate the benefits of these long accurate reads as well as for development of bioinformatic tools including genome assemblers, variant callers, and haplotyping algorithms. We present deep coverage HiFi datasets for five complex samples including the two inbred model genomes Mus musculus and Zea mays, as well as two complex genomes, octoploid Fragaria × ananassa and the diploid anuran Rana muscosa. Additionally, we release sequence data from a mock metagenome community. The datasets reported here can be used without restriction to develop new algorithms and explore complex genome structure and evolution. Data were generated on the PacBio Sequel II System.

Artificial intelligence in oral and maxillofacial radiology: what is currently possible?

Artificial intelligence, which has been actively applied in a broad range of industries in recent years, is an active area of interest for many researchers. Dentistry is no exception to this trend, and the applications of artificial intelligence are particularly promising in the field of oral and maxillofacial (OMF) radiology. Recent researches on artificial intelligence in OMF radiology have mainly used convolutional neural networks, which can perform image classification, detection, segmentation, registration, generation, and refinement. Artificial intelligence systems in this field have been developed for the purposes of radiographic diagnosis, image analysis, forensic dentistry, and image quality improvement. Tremendous amounts of data are needed to achieve good results, and involvement of OMF radiologist is essential for making accurate and consistent data sets, which is a time-consuming task. In order to widely use artificial intelligence in actual clinical practice in the future, there are lots of problems to be solved, such as building up a huge amount of fine-labeled open data set, understanding of the judgment criteria of artificial intelligence, and DICOM hacking threats using artificial intelligence. If solutions to these problems are presented with the development of artificial intelligence, artificial intelligence will develop further in the future and is expected to play an important role in the development of automatic diagnosis systems, the establishment of treatment plans, and the fabrication of treatment tools. OMF radiologists, as professionals who thoroughly understand the characteristics of radiographic images, will play a very important role in the development of artificial intelligence applications in this field.

Monitoring of solar spectral ultraviolet irradiance in Aosta, Italy

Abstract. A Bentham DTMc300 spectroradiometer is deployed at the station of Aosta–Saint-Christophe, Italy, at the headquarters of the Regional Environmental Protection Agency (ARPA) and has been performing continuous high-quality spectral measurements of the solar ultraviolet (UV) irradiance since 2006. The measuring site is located in the north-western region of the Alps, on a large valley floor at the altitude of 570 m a.s.l., surrounded by mountains. It is very significant to have accurate measurements in such a sensitive environment, since the complex terrain and the strongly variable meteo-climatic conditions typical of the Alps induce large spatial and temporal variability in the surface levels of the solar UV irradiance. The spectroradiometer is also used as a reference of a regional UV network, with additional stations located at different altitudes (1640 and 3500 m a.s.l.) and environmental conditions (mountain and glacier). In the present study we discuss the procedures and the technical aspects which ensure the high quality of the measurements performed by the reference instrument and the procedures used to characterize the Bentham. The quality control and quality assurance (QA–QC) procedures are also discussed. We show that the good quality of the spectral measurements is further ensured by a strong traceability chain to the irradiance scale of the Physikalisch-Technische Bundesanstalt (PTB) and a strict calibration protocol. Recently, the spectral UV dataset of Aosta–Saint-Christophe has been re-evaluated and homogenized. The final spectra constitute one of the most accurate datasets globally. At wavelengths above 310 nm and for solar zenith angles below 75∘, the expanded (k=2) uncertainty in the final dataset decreases with time, from 7 % in 2006 to 4 % in the present. The present study not only serves as the reference document for any future use of the data, but also provides useful information for experiments and novel techniques which have been applied for the characterization of the instrument and the QA–QC of the spectral UV measurements. Furthermore, the study clearly shows that maintaining a strong traceability chain to a reference scale of spectral irradiance is critical for the good quality of the measurements. The studied spectral dataset is freely accessible at https://doi.org/10.5281/zenodo.4028907 (Fountoulakis et al., 2020b).

Revisiting the coupon collector’s problem to unveil users’ online sessions in networked systems

Accuratecomprehension of users’ behavior is paramount for understanding the dynamics of several systems, such as e-commerce platforms, social networks, and mobile computing. To this end, several strategies have been proposed to obtain data sets based on the capture of usage information, which can then serve for user analytics. A popular strategy consists of taking periodic snapshots of online users, a practical instance of the coupon collector’s problem tailored to users monitoring in networked systems. Due to system-specific limitations, however, users may fail to appear in some snapshots, although online. To bridge this gap, we present a methodology to correct ill-collected snapshots and build more accurate data sets. In summary, we formally model user snapshotting as an instance of the coupon collector’s problem, estimate the probability that some users are missing in a given snapshot following a Bernoulli process, and correct those snapshots should the probability exceed a given threshold.

A Methodology and Tool for Mapping the Risk of Cumulative Effects on Benthic Habitats

The implementation of the European integrated marine policy poses many scientific challenges. Among them, the knowledge and understanding of interactions between anthropogenic pressures and ecological components is an important issue, particularly to help define Good Environmental Status, environmental targets and monitoring programs of the Marine Strategy Framework Directive (2008, MSFD). Cumulative effects assessment is a particularly complex issue requiring modeling tools and methods, as well as accurate data sets on human activities, anthropogenic pressures and ecological components. The results of these assessments are also uncertain and highly dependent on the calculation methods and assumptions, as well as on the data sets used. Within this context, we developed a technical and methodological approach to map the risk of cumulative effects on benthic habitats. These developments were initiated as part of the implementation of the MSFD to contribute to the diagnosis of the marine environment. Here we provide a demonstrator to illustrate the feasibility for mapping the risk of cumulative effects on benthic habitats, as well as the confidence index and the variability associated with this analysis. The method is based on a spatial analysis using a mapping of benthic habitats and their sensitivity to pressures, as well as the distribution and intensity of human activities and associated pressures. We collected and prepared relatively accurate and consistent data sets to describe human activities and benthic habitats. Data sets are embedded into a grid that facilitates the management and analysis of the data and exploitation of the results. The demonstrator consists of a relational database using the Spatial Query Language (SQL) language as well as data analysis scripts using the R language. The first demonstrator operations validated the main methodological and technical choices and helped to identify future developments needed to facilitate the appropriation and integration of these approaches in the implementation of public policies for the management of the marine environment.

Optimal Lateral Displacement in Automatic Close-Range Photogrammetry.

Based on the use of automatic photogrammetry, different researchers made evident that the level of overlap between adjacent photographs directly affects the uncertainty of the 3D dense cloud originated by the Structure from Motion/Image Matching (SfM/IM) process. The purpose of this study was to investigate if, in the case of a convergent shooting typical of close-range photogrammetry, an optimal lateral displacement of the camera for minimizing the 3D data uncertainty could be identified. We examined five different test objects made of rock, differing in terms of stone type and visual appearance. First, an accurate reference data set was generated by acquiring each object with an active range device, based on pattern projection (σz = 18 µm). Then, each object was 3D-captured with photogrammetry, using a set of images taken radially, with the camera pointing to the center of the specimen. The camera–object minimum distance was kept at 200 mm during the shooting, and the angular displacement was as small as π/60. We generated several dense clouds by sampling the original redundant sequence at angular displacements (nπ/60, n = 1, 2, … 8). Each 3D cloud was then compared with the reference, implementing an accurate scaling protocol to minimize systematic errors. The residual standard deviation of error made consistently evident a range of angular displacements among images that appear to be optimal for reducing the measurement uncertainty, independent of each specimen shape, material, and texture. Such a result provides guidance about how best to arrange the cameras’ geometry for 3D digitization of a stone cultural heritage artifact with several convergent shots. The photogrammetric tool used in the experiments was Agisoft Metashape.

A New Long-Term Downward Surface Solar Radiation Dataset over China from 1958 to 2015.

Downward surface solar radiation (Rs) plays a dominant role in determining the climate and environment on the Earth. However, the densely distributed ground observations of Rs are usually insufficient to meet the increasing demand of the climate diagnosis and analysis well, so it is essential to build a long-term accurate Rs dataset. The extremely randomized trees (ERT) algorithm was used to generate Rs using routine meteorological observations (2000–2015) from the Climate Data Center of the Chinese Meteorological Administration (CDC/CMA). The estimated Rs values were validated against ground measurements at the national scale with an overall correlation coefficient value of 0.97, a mean bias of 0.04 Wm−2, a root-mean-square-error value of 23.12 Wm−2, and a mean relative error of 9.81%. It indicates that the estimated Rs from the ERT-based model is reasonably accurate. Moreover, the ERT-based model was used to generate a new daily Rs dataset at 756 CDC/CMA stations from 1958 to 2015. The long-term variation trends of Rs at 454 stations covering 46 consecutive years (1970–2015) were also analyzed. The Rs in China showed a significant decline trend (−1.1 Wm−2 per decade) during 1970–2015. A decreasing trend (−2.8 Wm−2 per decade) in Rs during 1970–1992 was observed, followed by a recovery trend (0.23 Wm−2 per decade) during 1992–2015. The recovery trends at individual stations were found at 233 out of 454 stations during 1970–2015, which were mainly located in southern and northern China. The new Rs dataset would substantially provide basic data for the related studies in agriculture, ecology, and meteorology.

Development of a Machine-Learning Model of Short-Term Prognostic Prediction for Spinal Stenosis Surgery in Korean Patients.

Background: In this study, based on machine-learning technology, we aim to develop a predictive model of the short-term prognosis of Korean patients who received spinal stenosis surgery. Methods: Using the data obtained from 112 patients with spinal stenosis admitted at N hospital from February to November, 2019, a predictive analysis was conducted for the pain index, reoperation, and surgery time. Results: Results show that the predicted area under the curve was 0.803, 0.887, and 0.896 for the pain index, reoperation, and surgery time, respectively, thereby indicating the accuracy of the model. Conclusion: This study verified that the individual characteristics of the patient and treatment characteristics during surgery enable a prediction of the patient prognosis and validate the accuracy of the approach. Further studies should be conducted to extend the scope of this research by incorporating a larger and more accurate dataset.