Template Database Research Articles

Development of a database structure for the first Geomorphological map of Greece at 1:1,000,000 scale

Geomorphological maps offer researchers multiple advantages when studying an area, as they can provide insights into the formation processes of the observed landforms, as well as their possible evolution in the future. The geodatabase seems to be of primary importance, as it determines the way in which the data will be organized and presented on a map, and thus the map’s functionality. There are not specific guidelines for a database for geomorphological maps, as this would be dependent, inter alia, on the scale of the maps. However, up to this day, there is not a single data base template to be used for geomorphological mapping. In each case, the cartographer/geomorphologist determines the number of fields their layers will have and their type, as well as what information they will contain, depend-ing on the scale they are working on, the variety of landforms of their area, the time and resources available (correspondingly, the accuracy their map will have) and the purpose of its creation. Also, while several countries - not only large ones, but smaller ones as well - do have a geomorphological map at national scale, many countries, Greece among them, do not. On the contrary, only parts of them have been mapped by various researchers, who did not share any common database, which renders the combination of the individual maps difficult. But even in countries with existent national geomorphological maps, a specific and common geodatabase structure was not followed. In this way, there is no uniformity in the data and comparisons between maps, as well as combinations of data are very difficult and require a lot of work. Therefore, as we have initiated a project to create the geomorphological map of the Greek territory at 1:1,000,000 scale, we found that, prior to the beginning of the mapping, it was imperative to create a geodatabase template which we intend to follow, and which can be used as a template for geomorphological mapping at national scale by other countries (researchers and/or authorities). Thus, in this paper, we propose a database template to be used in geomorphological mapping at global scale globally, so that the data and structure of maps share common properties, thus allowing for comparisons and combina-tions of data where necessary.

Simplifying Multimodal Clinical Research Data Management: Introducing an Integrated and User-friendly Database Concept.

Clinical research, particularly in scientific data, grapples with the efficient management of multimodal and longitudinal clinical data. Especially in neuroscience, the volume of heterogeneous longitudinal data challenges researchers. While current research data management systems offer rich functionality, they suffer from architectural complexity that makes them difficult to install and maintain and require extensive user training. The focus is the development and presentation of a data management approach specifically tailored for clinical researchers involved in active patient care, especially in the neuroscientific environment of German university hospitals. Our design considers the implementation of FAIR (Findable, Accessible, Interoperable, and Reusable) principles and the secure handling of sensitive data in compliance with the General Data Protection Regulation. We introduce a streamlined database concept, featuring an intuitive graphical interface built on Hypertext Markup Language revision 5 (HTML5)/Cascading Style Sheets (CSS) technology. The system can be effortlessly deployed within local networks, that is, in Microsoft Windows 10 environments. Our design incorporates FAIR principles for effective data management. Moreover, we have streamlined data interchange through established standards like HL7 Clinical Document Architecture (CDA). To ensure data integrity, we have integrated real-time validation mechanisms that cover data type, plausibility, and Clinical Quality Language logic during data import and entry. We have developed and evaluated our concept with clinicians using a sample dataset of subjects who visited our memory clinic over a 3-year period and collected several multimodal clinical parameters. A notable advantage is the unified data matrix, which simplifies data aggregation, anonymization, and export. THIS STREAMLINES DATA EXCHANGE AND ENHANCES DATABASE INTEGRATION WITH PLATFORMS LIKE KONSTANZ INFORMATION MINER (KNIME): . Our approach offers a significant advancement for capturing and managing clinical research data, specifically tailored for small-scale initiatives operating within limited information technology (IT) infrastructures. It is designed for immediate, hassle-free deployment by clinicians and researchers.The database template and precompiled versions of the user interface are available at: https://github.com/stebro01/research_database_sqlite_i2b2.git.

3D Reconstruction of Wheat Plants by Integrating Point Cloud Data and Virtual Design Optimization

The morphology and structure of wheat plants are intricate, containing numerous tillers, rich details, and significant cross-obscuration. Methods of effectively reconstructing three-dimensional (3D) models of wheat plants that reflects the varietal architectural differences using measured data is challenging in plant phenomics and functional–structural plant models. This paper proposes a 3D reconstruction technique for wheat plants that integrates point cloud data and virtual design optimization. The approach extracted single stem number, growth position, length, and inclination angle from the point cloud data of a wheat plant. It then built an initial 3D mesh model of the plant by integrating a wheat 3D phytomer template database with variety resolution. Diverse 3D wheat plant models were subsequently virtually designed by iteratively modifying the leaf azimuth, based on the initial model. Using the 3D point cloud of the plant as the overall constraint and setting the minimum Chamfer distance between the point cloud and the mesh model as the optimization objective, we obtained the optimal 3D model as the reconstruction result of the plant through continuous iterative calculation. The method was validated using 27 winter wheat plants, with nine varieties and three replicates each. The R2 values between the measured data and the reconstructed plants were 0.80, 0.73, 0.90, and 0.69 for plant height, crown width, plant leaf area, and coverage, respectively. Additionally, the Normalized Root Mean Squared Errors (NRMSEs) were 0.10, 0.12, 0.08, and 0.17, respectively. The Mean Absolute Percentage Errors (MAPEs) used to investigate the vertical spatial distribution between the reconstructed 3D models and the point clouds of the plants ranged from 4.95% to 17.90%. These results demonstrate that the reconstructed 3D model exhibits satisfactory consistency with the measured data, including plant phenotype and vertical spatial distribution, and accurately reflects the characteristics of plant architecture and spatial distribution for the utilized wheat cultivars. This method provides technical support for research on wheat plant phenotyping and functional–structural analysis.

Anti-Software Attack Ear Identification System Using Deep Feature Learning and Blockchain Protection

Ear recognition has made good progress as an emerging biometric technology. However, the recognition performance, generalization ability, and feature robustness of ear recognition systems based on hand-crafted features are relatively poor. With the development of deep learning, these problems have been partly overcome. However, the recognition performance of existing ear recognition systems still needs to be improved when facing unconstrained ear databases in realistic scenarios. Another critical problem is that most systems with ear feature template databases are vulnerable to software attacks that disclose users’ privacy and even bring down the system. This paper proposes a software-attack-proof ear recognition system using deep feature learning and blockchain protection to address the problem that the recognition performance of existing systems is generally poor in the face of unconstrained ear databases in realistic scenarios. First, we propose an accommodative DropBlock (AccDrop) to generate drop masks with adaptive shapes. It has an advantage over DropBlock in coping with unconstrained ear databases. Second, we introduce a simple and parameterless attention module that uses 3D weights to refine the ear features output from the convolutional layer. To protect the security of the ear feature template database and the user’s privacy, we use Merkle tree nodes to store the ear feature templates, ensuring the determinism of the root node in the smart contract. We achieve Rank-1 (R1) recognition accuracies of 83.87% and 96.52% on the AWE and EARVN1.0 ear databases, which outperform most advanced ear recognition systems.

Novel autosomal dominant TMC1 variants linked to hearing loss: insight into protein-lipid interactions

BackgroundTMC1, which encodes transmembrane channel-like protein 1, forms the mechanoelectrical transduction (MET) channel in auditory hair cells, necessary for auditory function. TMC1 variants are known to cause autosomal dominant (DFNA36) and autosomal recessive (DFNB7/11) non-syndromic hearing loss, but only a handful of TMC1 variants underlying DFNA36 have been reported, hampering analysis of genotype-phenotype correlations.MethodsIn this study, we retrospectively reviewed 338 probands in an in-house database of genetic hearing loss, evaluating the clinical phenotypes and genotypes of novel TMC1 variants associated with DFNA36. To analyze the structural impact of these variants, we generated two structural models of human TMC1, utilizing the Cryo-EM structure of C. elegans TMC1 as a template and AlphaFold protein structure database. Specifically, the lipid bilayer-embedded protein database was used to construct membrane-embedded models of TMC1. We then examined the effect of TMC1 variants on intramolecular interactions and predicted their potential pathogenicity.ResultsWe identified two novel TMC1 variants related to DFNA36 (c.1256T > C:p.Phe419Ser and c.1444T > C:p.Trp482Arg). The affected subjects had bilateral, moderate, late-onset, progressive sensorineural hearing loss with a down-sloping configuration. The Phe419 residue located in the transmembrane domain 4 of TMC1 faces outward towards the channel pore and is in close proximity to the hydrophobic tail of the lipid bilayer. The non-polar-to-polar variant (p.Phe419Ser) alters the hydrophobicity in the membrane, compromising protein-lipid interactions. On the other hand, the Trp482 residue located in the extracellular linker region between transmembrane domains 5 and 6 is anchored to the membrane interfaces via its aromatic rings, mediating several molecular interactions that stabilize the structure of TMC1. This type of aromatic ring-based anchoring is also observed in homologous transmembrane proteins such as OSCA1.2. Conversely, the substitution of Trp with Arg (Trp482Arg) disrupts the cation-π interaction with phospholipids located in the outer leaflet of the phospholipid bilayer, destabilizing protein-lipid interactions. Additionally, Trp482Arg collapses the CH-π interaction between Trp482 and Pro511, possibly reducing the overall stability of the protein. In parallel with the molecular modeling, the two mutants degraded significantly faster compared to the wild-type protein, compromising protein stability.ConclusionsThis results expand the genetic spectrum of disease-causing TMC1 variants related to DFNA36 and provide insight into TMC1 transmembrane protein-lipid interactions.

Enhanced Template Protection Algorithms Based on Fuzzy Vault and Cuckoo Hashing for Fingerprint Biometrics

Biometrics provides better authentication. Unprotected biometrics is open to attacks from intruders as stolen biometrics may not be revocable. Although there are several points where attacks can be launched on biometric systems, template databases are said to be the most frequently attacked. When a template database is attacked, attackers can add fresh templates, modify the existing ones, copy or steal templates and later construct a spoof from it or replay it back into the biometric system to impersonate a genuine user. Several template security systems have been presented in the literature to secure biometric templates. Fuzzy vault, as proposed by many researchers is, to some extent, one of the best algorithms to achieve template protection as it has good security. Fuzzy vault, however, lacks irreversibility, revocability, and diversity. To address these disadvantages and strengthen fuzzy vault, this study combines a noninvertible feature transformation template protection algorithm known as cuckoo hashing that possesses irreversibility, revocability, and diversity properties with a fuzzy vault for privacy. The study used fingerprint biometrics as it is widely used. The proposed algorithm was implemented in the MATLAB 2016a environment using FVC 2004 DB1 fingerprint public database. The proposed algorithm recorded a FAR of 0.01% and an FRR value of 0.09% with an EER of 0.05%.

Video Sensor-Based Automatic License Plate Recognition of Static and Moving Vehicles

In Bangladesh, present transportation system needs suitable control schemes to ensure safety and mobility to the road users. License Plate Recognition (LPR) is one of the control schemes which can be used to ensure road safety using video sensors. Moreover, from installation point of view, it is cheaper than Radiofrequency Identification (RFID) system. Automated LPR is adopted to reduce human involvement which causes loss in accuracy and reliability in reading license plate. The extracted information from LPR can be used in various schemes, such as electronic payment system, traffic surveillance and extracting vehicle trajectory. In this paper, we are presenting an offline dynamic LPR system, which uses geometric properties of Bengali alphabets stored in alphabet template database to recognize license plates from video. The system comprises of three main components: 1) License Plate Locating (LPL), 2) Character Segmentation (CS), and 3) Geometric Character Recognition (GCR). In this regard, the image is converted into a binary image considering morphological operations and color modification. A new ratio-based detection algorithm has been proposed for the segmentation of license plate. Finally, the alphabet template database and the character extracted from detected license plate are correlated to recognize alphanumeric character which deduces the plate number. Thus, the plate number can be utilized for further action.

Factors of cognitive complexity of test questions in psychophysiological studies

The paper presents the results of a study of the functional state evaluations of the brain during auditory perception. The subjects listened 60 questions with different linguistic characteristics, taken from polygraph database templates, and answered to them. This characteristics: is the number of different types of words, the percentage of words from different parts of speech, the number of negations, the presence of forms of personal pronouns and their place in the question, the number of letters, the percentage of vowels, the position of intonational stress. As psychological characteristics that affect the functional state of the brain, the following were measured: verbal intelligence according to the R.Amthauer’s test, personal and situational anxiety according to the Spielberger — Khanin test. To measure the functional state of the brain, a 19-channel EEG was recorded in the 10–20% system. The functional state of the brain was assessed by calculating the fractal dimension of the EEG using the method. The sample consisted of students and employees of a number of educational institutions in St Petersburg, 9 men and 8 women aged 19 to 59 years. An analysis of the experimental data made it possible to confirm the hypothesis about the influence of the measured questionnaire characteristics, the linguistic characteristics of the questions, and the psychological characteristics of the subjects on the fractal dimension of the EEG. EEG analysis in various leads revealed two EEG “complexity” factors related to the frontal and occipital areas of the brain. A regression model was obtained for assessing the cognitive complexity of a particular test question, which is reflected in the complexity of the EEG curve of the subject perceiving this question. The resulting model allows you to select questions for psychophysiological examination that have the required level of cognitive complexity. The results of the work testify to the importance of such an indicator as the fractal dimension of the EEG for studying the functional state of the brain and its dependence both on the personal and biological characteristics of a person, and on the emotional state and complexity of the information received by the analyzers.

862 Process Mapping of 3D Printing for Complex Limb Problems

Abstract Introduction Difficult limb problems such as complex trauma or re-presentation following orthopaedic revision surgeries can present substantial planning and technical challenges. 3D-printed models built from patient-specific CT scans facilitate creative thinking, problem solving and decision making to find better operative solutions. This quality improvement project aims to map the process of using 3D printers to solve orthopaedic problems. Method Stakeholders, including a Consultant Trauma & Orthopaedic surgeon and the Medical Physics team were interviewed to formalise the full structure of their role from start to end, with the support of the Trust's Improvement Team and Innovation Team. A visual representation of the process map was produced using SmartDraw software. Feedback was received from stakeholders and a second cycle of process mapping was completed. Results The process map included the chronological steps of the project, the interaction between different roles and the stages of 3D printing. A database template was produced as a shared OneNote, allowing the tracking of each model production. Stakeholders found the map useful for anticipating problems and considering the future process and providing a framework of implementing innovation within the NHS. Discussion Unique implants cost the NHS significantly more money than batch-made products. Introduction of 3D models into pre-operative planning allow surgeons to utilise readily available solutions instead of custom, single-use implants, which can be cost saving and prevents unnecessary wastage. The project trialled operations on models, facilitated patient explanations and provided an educational tool. Future aims include roll-out to other specialties and Trusts, encouraging collaboration towards a sustainable internal economy.

Vfold-Pipeline: a web server for RNA 3D structure prediction from sequences.

RNA 3D structures are critical for understanding their functions and for RNA-targeted drug design. However, experimental determination of RNA 3D structures is laborious and technically challenging, leading to the huge gap between the number of sequences and the availability of RNA structures. Therefore, the computer-aided structure prediction of RNA 3D structures from sequences becomes a highly desirable solution to this problem. Here, we present a pipeline server for RNA 3D structure prediction from sequences that integrates the Vfold2D, Vfold3D and VfoldLA programs. The Vfold2D program can incorporate the SHAPE experimental data in 2D structure prediction. The pipeline can also automatically extract 2D structural constraints from the Rfam database. Furthermore, with a significantly expanded 3D template database for various motifs, this Vfold-Pipeline server can efficiently return accurate 3D structure predictions or reliable initial 3D structures for further refinement. http://rna.physics.missouri.edu/vfoldPipeline/index.html. The data underlying this article have been provided in the article and in its online supplementary material. Supplementary data are available at Bioinformatics online.

A recursive matched-filter to systematically explore volcanic long-period earthquake swarms

SummaryThe matched-filter technique is an effective way to detect repeats, or near-repeats, of a seismic source, but prior identification of an event from that source to use as a template is required. We propose a recursive matched-filter approach to systematically explore earthquake swarms, here applied to a swarm of volcanic long-period seismicity beneath Mount Sidley in Antarctica. We start with a single visually chosen template event with a high signal-to-noise ratio. We then extend our template database by selecting new templates to use in a subsequent matched-filter search from the newly detected set of events, allowing us to recursively expand the number of templates. We demonstrate that each iteration of the matched-filter search progressively extends the spatial coverage of our set of templates away from the original template event. In such a way, our proposed method overcomes the matched-filter search’s strictest constraint: that an event must already be identified to detect other similar events. Our recursive matched-filtering approach is well suited for the systematic exploration of earthquake swarms in both volcanic and tectonic contexts.

Last interglacial sea-level proxies in the Korean Peninsula

Abstract. Like most of the world's coastlines, the Korean Peninsula experienced higher-than-present sea levels during the last interglacial (LIG), otherwise known as Marine Isotope Stage (MIS) 5e. However, the expression of that highstand in the geological record differs across the eastern and western Korean Peninsula. The tectonically active east coast of the Korean Peninsula is characterized by broad uplifted marine terraces, while the stable west coast is characterized by tidal flats and rias. In this study, we used a standardized database template to review and extract the existing constraints on LIG sea levels along both the east and west coasts of the Korean Peninsula. A total of 62 LIG constraining data points were compiled including 34 sea-level indicators, 22 marine limiting records, and 6 terrestrial limiting records. The ages from these data points are based on 61 optically stimulated luminescence (OSL) measurements and 1 paleomagnetic-based age. Along the uplifted east coast, LIG sea-level indicators based on marine terraces are at elevations ranging from +9 to +32 m. The uplifted marine terraces are cut or otherwise deformed by faults developed under a compressional regime due to back-arc closing of the East Sea since the early Pliocene. As a result, tectonic uplift likely has affected the elevations of the east coast LIG shorelines. In contrast, LIG sea-level records on the west coast of the Korean Peninsula are found at heights of between +3 and +6 m and include marine and terrestrial elevation limiting records as well as true sea-level indicators. The LIG sea-level constraints along the west coast of the Korean Peninsula are likely unaffected by vertical movement or experienced minor subsidence during the Quaternary. The database is available open access at https://doi.org/10.5281/zenodo.4974826 (Ryang and Simms, 2021).

Influence of Template Size, Canonicalization, and Exclusivity for Retrosynthesis and Reaction Prediction Applications.

Heuristic and machine learning models for rank-ordering reaction templates comprise an important basis for computer-aided organic synthesis regarding both product prediction and retrosynthetic pathway planning. Their viability relies heavily on the quality and characteristics of the underlying template database. With the advent of automated reaction and template extraction software and consequently the creation of template databases too large for manual curation, a data-driven approach to assess and improve the quality of template sets is needed. We therefore systematically studied the influence of template generality, canonicalization, and exclusivity on the performance of different template ranking models. We find that duplicate and nonexclusive templates, i.e., templates which describe the same chemical transformation on identical or overlapping sets of molecules, decrease both the accuracy of the ranking algorithm and the applicability of the respective top-ranked templates significantly. To remedy the negative effects of nonexclusivity, we developed a general and computationally efficient framework to deduplicate and hierarchically correct templates. As a result, performance improved considerably for both heuristic and machine learning template ranking models, as well as multistep retrosynthetic planning models. The canonicalization and correction code is made freely available.

A Novel Minutiae Triangulation Technique for Non-invertible Fingerprint Template Generation

The fingerprint is the readily available and most widely used biometrics for the security of a system. In order to impart the security of the template database, it is important to make the fingerprint template robust to fingerprint reconstruction, i.e., invertibility. In this paper, a fingerprint template is proposed using a novel minutiae triangulation technique. In this triangulation technique, the set of minutiae of a template is taken to generate a set of minutiae triplets each forming a triangle. After this, a minutiae transformation is applied to obtain a set of triplets of internal angles of the triangle which also removes the minutiae location and orientation information. In the absence of this information, the orientation map of the fingerprint cannot be estimated. This set of triplets together with some other information is used as a proposed fingerprint template. The proposed system is experimented using standard FVC2000, FVC2004 and FVC2006 databases and yields better results in terms of EER (Equal Error Rate) as compared with the state-of-art techniques.

Last interglacial sea levels within the Gulf of Mexico and northwestern Caribbean Sea

Abstract. During the last interglacial (LIG) the volume of additional water in the world's oceans was large enough to raise global sea levels about 6–9 m higher than present levels. However, LIG sea levels vary regionally and those regional differences hold clues about the past distribution of ice sheets and local rates of subsidence and tectonic uplift. In this study, I used a standardized database template to review and summarize the existing constraints on LIG sea levels across the northern Gulf of Mexico and Caribbean shoreline of the Yucatán Peninsula. In total, I extracted 32 sea-level indicators including the insertion of 16 U-series ages on corals, 1 electron spin resonance age, 2 amino acid racemization ages, and 26 luminescence ages. Most dated sea-level indicators for the northern Gulf of Mexico are based on optically stimulated luminescence (OSL) ages of beach deposits of a mappable LIG shoreline. This shoreline extends from the Florida Panhandle through south Texas but is buried or removed by the Mississippi River across most of Louisiana. A similar feature is observed in satellite images south of the Rio Grande within the Mexican portions of the Gulf of Mexico but has yet to be dated. Elevations measured on portions of this feature close to the modern coast point to sea levels less than 1 m to ∼5 m higher than present for much of the northern Gulf of Mexico. However, a few, albeit undated, portions of the same shoreline located at more inland locations point to sea levels up to +7.2 m, attesting to up to 7 m of differential subsidence between the inland and coastal sites. Across the Yucatán Peninsula, U-series dating of corals has provided the main index points for LIG sea levels. Other carbonate coastal features such as beach ridges and eolianites have also been described but rely on corals for their dating. The maximum elevation of the LIG coral-based relative sea-level (RSL) estimates decrease from around +6 m across the Caribbean shoreline of the Yucatán Peninsula near Cancún, Mexico, to as low as −6 m to the south beneath the southern atolls of Belize, although discussion continues as to the validity of the ages for these southern corals. If these lower-elevation corals are LIG in age, their below-present elevations may be a result of vertical motion along faults dipping into the Cayman Trough. South of Belize only one purported LIG coral has been dated on the Isla de Roatán off the coast of Honduras at a likely tectonically uplifted elevation of 37.2 m. Thus the elevation of LIG sea levels within the inland siliciclastic shorelines of Guatemala and Honduras as well as the southwestern Gulf of Mexico remains poorly constrained and a potential venue for future research. The database described in this paper is available open access in spreadsheet format as Simms (2020), at this link: https://doi.org/10.5281/zenodo.4556163.

TBDBT: A TB DataBase Template for collection of harmonized TB clinical research data in REDCap, facilitating data standardisation for inter-study comparison and meta-analyses.

Clinical tuberculosis research, both within research groups and across research ecosystems, is often undertaken in isolation using bespoke data collection platforms and applying differing data conventions. This failure to harmonise clinical phenotype data or apply standardised data collection and storage standards in turn limits the opportunity to undertake meta-analyses using data generated across multiple research projects for the same research domain. We have developed the Tuberculosis DataBase Template (TBDBT), a template for the well-supported, free and commonly deployed clinical databasing platform, REDCap. This template can be used to set up a new tuberculosis research database with a built-in set of standardised data conventions, to ensure standardised data capture across research projects and programs. A modular design enables researchers to implement only the modules of the database template that are appropriate for their particular study. The template includes core modules for informed consent data, participant demographics, clinical symptoms and presentation, diagnostic imaging and laboratory tests. Optional modules have been designed for visit scheduling and calendar functionality, clinical trial randomisation, study logistics and operations, and pharmacokinetic data. Additional fields can be added as needed. This REDCap template can facilitate collection of high-quality data for tuberculosis research, providing a tool to ensure better data harmonisation, analysis and meta-analysis.

Robustification of RosettaAntibody and Rosetta SnugDock.

In recent years, the observed antibody sequence space has grown exponentially due to advances in high-throughput sequencing of immune receptors. The rise in sequences has not been mirrored by a rise in structures, as experimental structure determination techniques have remained low-throughput. Computational modeling, however, has the potential to close the sequence-structure gap. To achieve this goal, computational methods must be robust, fast, easy to use, and accurate. Here we report on the latest advances made in RosettaAntibody and Rosetta SnugDock-methods for antibody structure prediction and antibody-antigen docking. We simplified the user interface, expanded and automated the template database, generalized the kinematics of antibody-antigen docking (which enabled modeling of single-domain antibodies) and incorporated new loop modeling techniques. To evaluate the effects of our updates on modeling accuracy, we developed rigorous tests under a new scientific benchmarking framework within Rosetta. Benchmarking revealed that more structurally similar templates could be identified in the updated database and that SnugDock broadened its applicability without losing accuracy. However, there are further advances to be made, including increasing the accuracy and speed of CDR-H3 loop modeling, before computational approaches can accurately model any antibody.

PlexNet: An Ensemble of Deep Neural Networks for Biometric Template Protection

The security of biometric systems, especially pro-tecting the templates stored in the gallery database, is a primary concern for researchers. This paper presents a novel framework using an ensemble of deep neural networks to protect biometric features stored as a template. The proposed ensemble chooses two state-of-the-art CNN architectures i.e., ResNet and DenseNet as base models for training. While training, the pre-trained weights enable the learning algorithm to converge faster. The weights obtained through the base model is further used to train other compatible models, generating a fine-tuned model. Thus, four fine-tuned models are prepared, and their learning are fused to form an ensemble named as PlexNet. To analyze biometric templates’ security, the rigorous learning of ensemble is collected using a smart box i.e., application programming interface (API). The API is robust and correctly identifies the query image without referring to a template database. Thus, the proposed framework excludes the templates from database and performed predictions based on learning that is irrevocable.

Design and implementation of the system to support making medical decisions aid to the population

The publication discusses the issues and results of designing an automated system for supporting medical decision-making on issues of antirabic prevention and aid to the population. The need to provide medical care in the framework of preventing deaths from rabies infection and carrying out preventive measures to prevent such infections is relevant not only in the Russian Federation, but also in many countries of the world. Algorithms for providing medical care and carrying out rabies vaccination are complex, requiring certain professional skills from medical professionals, as well as care and accuracy from patients. Therefore, in manual mode, they are time-consuming both in terms of registering information about the treatment performed, and in terms of the speed of forming medical decisions when providing medical care or when correcting violations of previously defined algorithms. For computer support of these processes, an automated system for supporting medical decision-making has been developed using the tools of the Clarion 10 relational database management system. For various categories of patients and citizens undergoing rabies prevention, experts have developed and entered into the database templates of treatment courses, which are assigned by the system after analyzing the clinical data of patients and the initial or repeated fact of their request for help. These templates and algorithms for analyzing the possibilities of their application are similar to products that allow you to link assumptions and conclusions when making decisions. The automated medical decision support system allows you to register patients and persons undergoing rabies prevention, assign them treatment courses and vaccination schemes, adjust treatment and prevention methods in case of violations of previously prescribed ones, and generate statistical reports. The developed software product received the author’s certificate no. 2018663452 dated 26.10.2018 from the Federal service for intellectual property (Rospatent). The software product has been tested in first aid rooms in Moscow, in the practice of the polyclinic department of the First City hospital named after N. I. Pirogov.

Radar group target recognition based on HRRPs and weighted mean shift clustering

When range high-resolution radar is applied to target recognition, it is quite possible for the high-resolution range profiles (HRRPs) of group targets in a beam to overlap, which reduces the target recognition performance of the radar. In this paper, we propose a group target recognition method based on a weighted mean shift (weighted-MS) clustering method. During the training phase, subtarget features are extracted based on the template database, which is established through simulation or data acquisition, and the features are fed to the support vector machine (SVM) classifier to obtain the classifier parameters. In the test phase, the weighted-MS algorithm is exploited to extract the HRRP of each subtarget. Then, the features of the subtarget HRRP are extracted and used as input in the SVM classifier to be recognized. Compared to the traditional group target recognition method, the proposed method has the advantages of requiring only a small amount of computation, setting parameters automatically, and having no requirement for target motion. The experimental results based on the measured data show that the method proposed in this paper has better recognition performance and is more robust against noise than other recognition methods.