Proven Solutions Research Articles

Enhanced biocompatibility and osseointegration properties of magnetron sputtered BTO-SZTO bio-piezoelectrically coated films as zirconium alloy implants

Bio-piezoelectric materials were capable of improving the osseointegration properties of implants by converting mechanical forces into electrical signals that provided microelectrical stimulation for the formation and remodeling of bone tissue. Although metallic bioimplant materials can provide adequate mechanical strength, their surfaces were biologically inert as well as lacking the piezoelectric properties to stimulate osteogenesis. In this study, perovskite piezoelectric materials (BaTiO3–SrZrTiO3) were uniformly deposited on the surface of a low-modulus zirconium alloy by magnetron sputtering, which endowed the surface of metallic biomaterials with favorable piezoelectric properties. Orthogonal tests were used to optimize the magnetron sputtering process parameters for the preparation of piezoelectric coatings. The morphology and electrical properties of the coated films were characterized by XRD, XPS, SEM, AFM and SKPFM. The piezoelectric constant of the piezoelectric coating prepared in this study was 5.02 pC/N, which approximated the piezoelectric properties of natural bone tissue. Biological experiments showed that the BaTiO3–SrZrTiO3 piezoelectric coated film had a good promotion effect on the early adhesion, proliferation and differentiation of osteoblasts. Compared with the traditional metal implant materials, this innovative method successfully simulated the piezoelectric properties of bone tissue on the material surface, resulting in better osseointegration properties of metal biomaterials. This method will provide a proven solution for surface modification of metallic implant materials.

Deep learning based data augmentation for large-scale mineral image recognition and classification

Vision-based mineral image recognition and classification is a proven solution for autonomous unmanned ore sorting. Although accurate identification can be achieved by training models offline using large-scale datasets, the lack of sufficient labeled images still limits the accessibility and exploration of high-performance deep learning models. To address the above issues, referring to the generative adversarial networks, three different deep learning-based mineral image data augmentation models are proposed in this work. The experimental results show that the proposed models can generate mineral images with high fidelity and have high similarity to the ground truth in terms of texture, color and shape. Compared with classic data augmentation methods, proposed ones can better optimize downstream sorting tasks: the accuracy of ResNet101, ResNet50, InceptionV3 and VGG19 is improved by 18.52%, 9.94%, 4.39% and 2.39%, respectively. Finally, this work also presents a monolithic three-stage system workflow for large-scale mineral image recognition and classification.

N-Days Tourist Route Recommender System in Yogyakarta Using Genetic Algorithm Method

Tourism is one of the proven solutions for the Indonesian economy. Tourism in certain regions, such as Yogyakarta, can significantly affect the region's economic development, including creating new jobs, creating new business opportunities, and increasing regional income. However, for tourists from outside Yogyakarta, it requires planning a tour before traveling in Yogyakarta, especially if he wants to spend several days on a tour. Many previous studies have developed systems that can recommend tourist routes, but not within a few days of tourist visits. In this study, we propose the use of Genetic Algorithm (GA) for automatically generating optimal travel itinerary for some days visit (n-days tour route). We develop the recommender system by combining GA and the concept of Multi-Attribute Utility Theory (MAUT). This MAUT used for accommodating user needs based some criteria such as rating, cost, and time. Based on our experimental results, GA is optimal in terms of execution time and number of attractions visited in n-days visit. The average execution time obtained is 59.62%, and the average number of attractions visited obtained is 45.95%. These results show that this method can generate tourist routes efficiently.

Data Provenance in Security and Privacy

Provenance information corresponds to essential metadata that describes the entities, users, and processes involved in the history and evolution of a data object. The benefits of tracking provenance information have been widely understood in a variety of domains; however, only recently have provenance solutions gained interest in the security community. Indeed, on the one hand, provenance allows for a reliable historical analysis enabling security-related applications such as forensic analysis and attribution of malicious activity. On the other hand, the unprecedented changes in the threat landscape place demands for securing provenance information to facilitate its trustworthiness.With the recent growth of provenance studies in security, in this work we examine the role of data provenance in security and privacy. To set this work in context, we outline fundamental principles and models of data provenance and explore how the existing studies achieve security principles. We further review the existing schemes for securing data provenance collection and manipulation known as secure provenance and the role of data provenance for security and privacy, which we refer to as threat provenance.

Mechanical and Environmental Performances of Warm Mix Asphalt with Reclaimed Asphalt and Plant-Based Binder

Abstract The environmental challenges facing society today are forcing the road construction industry to tackle the twin challenges of decreasing consumption of nonrenewable raw materials and limiting its carbon impacts. Yet, roadworks can deliver some genuine environmental benefits, along with low greenhouse gas emissions, by becoming a carbon sink. Recycling very high proportions of road construction materials and gradually incorporating bio-based products into their composition is now a proven solution. To this end, Eiffage Route has developed a range of plant-based binders, suitable for recycling, which incorporate a high proportion of materials recovered from existing pavement. This article reviews the so-called Biophalt innovation that won the 2019 award presented at the Road and Street Innovation Committee established by the Transport Infrastructure Department of the French Ministry of the Ecological Transition. It consists of a warm mix asphalt (WMA), including a high amount (>30 %) of recycled asphalt and a plant-based patented binder, suitable for any type of traffic. Both environmental and mechanical performances of Biophalt, assessed through SEVE TP modeling and several mix design studies carried out in the framework of different jobsites, are presented. They underline the “carbon sink” properties of the bio-based WMA as well as its compliance with standards defined by the norms of the French asphalt mix design method. It thus demonstrates Biophalt’s ability to combine both sustainability and excellent mechanical characteristics.

Design and Performance Analysis of a Novel Integrated Solar Combined Cycle (ISCC) with a Supercritical CO2 Bottom Cycle

The integrated solar combined cycle (ISCC) system is a proven solution for grid-connected power generation from solar energy. How to further improve the ISCC system efficiency and propose a more efficient system solution has become a research focus. A novel gas turbine combined cycle (GTCC) benchmark system is proposed by replacing the conventional steam Rankine bottom cycle with a supercritical CO2 Brayton cycle, whose output power and efficiency are increased by 9.07 MW and 1.3%, respectively, compared to those of the conventional GTCC system. Furthermore, the novel ISCC systems are established with the parabolic trough solar collector (PTC) and the solar tower (ST) collector coupled to the novel GTCC system. Thermal performance analysis, exergy performance analysis, and the sensitivity analysis of the ISCC systems have been performed, and the results show that the system efficiencies of both ISCC systems are lower than that of the GTCC system, at 57.1% and 57.5%, respectively, but the power generation of the ISCC system with PTC is greater than that of the benchmark system, while that of the ISCC system with ST is less than that of the benchmark system. The photoelectric efficiency of the ISCC system with PTC is 27.6%, which is 2.1% greater than that of ISCC system with ST. In the ISCC system with PTC, the components with the highest exergy destruction and the lowest exergy efficiency are the combustion chamber, and PTC, respectively. ST is the component with the highest exergy destruction and the lowest exergy efficiency in the ISCC system with ST. With the increase in direct normal irradiance (DNI), the total output power, solar energy output power, and photoelectric efficiency of the ISCC system with PTC increase, while the system efficiency decreases; the solar energy output power and photoelectric efficiency of the ISCC system with ST increase, while the total output power and system efficiency decrease. The photoelectric efficiency of the ISCC system with PTC is greater when the DNI is greater than 600 W/m2; conversely, the photoelectric efficiency of the ISCC system with ST is greater. After sensitivity analysis, the optimal intercooler pressure for the ISCC system is 11.3 MPa.

BLAST-IoT: BLockchain Assisted Scalable Trust in Internet of Things

Internet of Things (IoT) paved the way to realize ubiquitous access towards manifold services and applications by enabling connectivity between different physical devices. The devices, having heterogeneous computation power, protocol stack, or storage power, can send or receive various services by communicating through the internet. These services inevitably demand a secure and reliable network system to interchange the data or information for their impressive utilization. One proven solution to attain this objective is embedding Trust Management System (TMS) that aims to reduce risk or uncertainty associated with interacting adversary devices by capturing their dynamic behavior in the system. With TMS, devices compute and maintain trust value on the interacting devices by observing their behavior with different interaction instances. This trust information is exchanged between the devices to assess the global reputation of devices and facilitate devices’ decisions when there is a lack of direct interactions. For systems having enormous low-power devices, one crucial aspect of TMS is secure and timely dissemination, management, and storage of trust information to accurately assess devices’ dynamic behavior. Addressing this issue, we present a blockchain-assisted scalable trust model, BLAST-IoT, for IoT systems of heterogeneous devices in this paper. BLAST-IoT intends to ensure secure dissemination and storage of trust information leveraging on the functionalities provided by blockchain technology. It adopts a semi-distributed approach where direct trust information, computed by IoT end devices, is processed and stored by some high-power edge devices running public blockchain networks to handle impediments caused by power-deficient IoT devices. The effectiveness of BLAST-IoT has been evaluated through implementation and simulation-based results for trust convergence and assessment accuracy in the dynamic IoT environment. Further, the throughput performance of BLAST-IoT has been examined with an increase in network load.

ROPS commentary-Addressing our fatal blind spot: Applying evidence-based solutions to reduce the most frequent cause of death on U.S. farms.

Tractor overturns are the most prominent contributing factor to death on U.S. farms and have been for decades. While public health researchers hypothesized years ago that overturn fatalities would largely disappear as older tractors were replaced by newer ones, this has not happened. In the meantime, farmers continue to die in these easily preventable and tragic events. Not only are tractor rollover protective structures (ROPS) 99% effective in preventing death in the event of an overturn, a national program exists to connect farmers with ROPS. While this program has been popular with farmers, and the cost-effectiveness of providing farmers with technical support and cost-sharing rebates has been demonstrated, many states lack access to ROPS rebates, even those states with the highest number of overturn fatalities. Given the evidence, it is difficult to reconcile the lack of policy or public investment in a solution that decisively addresses the most pernicious contributor to death in the agricultural industry. In this commentary, we highlight the science behind this proven solution to tractor overturns and the essential role that the media and implementation science can play in encouraging policy-makers to save lives.

A Study of Influenced Factors toward Student Loyalty Among Private Universities in Kedah

Up to half of Malaysia's private higher education institutions could be forced to close if the country's private higher education sector were to collapse, leaving only those with substantial financial support to remain open. More than half of the country's small businesses have shut down due to the Covid-19 coronavirus, which has almost likely pushed the country into recession. This has worsened the prognosis for the already troubled university sector. Hence, student loyalty is another proven solution in combating these challenges. The purpose of this research is to look into and analyse the impact of service quality, university image, student satisfaction, and loyalty at private universities in Kedah, Malaysia. As this paper is a pilot study, therefore 150 questionnaires were distributed to target respondents. SPSS was used to analyse the 86 samples of private university students in the northern region of Malaysia. Findings postulate that only service quality, commitment and satisfaction affect a loyalty among private university student in northern region. This study helps institutions, teachers, and policymakers understand what makes private university students want for them to keep loyal with the universities.

Data Provenance in Biomedical Research: Scoping Review.

Data provenance refers to the origin, processing, and movement of data. Reliable and precise knowledge about data provenance has great potential to improve reproducibility as well as quality in biomedical research and, therefore, to foster good scientific practice. However, despite the increasing interest on data provenance technologies in the literature and their implementation in other disciplines, these technologies have not yet been widely adopted in biomedical research. The aim of this scoping review was to provide a structured overview of the body of knowledge on provenance methods in biomedical research by systematizing articles covering data provenance technologies developed for or used in this application area; describing and comparing the functionalities as well as the design of the provenance technologies used; and identifying gaps in the literature, which could provide opportunities for future research on technologies that could receive more widespread adoption. Following a methodological framework for scoping studies and the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines, articles were identified by searching the PubMed, IEEE Xplore, and Web of Science databases and subsequently screened for eligibility. We included original articles covering software-based provenance management for scientific research published between 2010 and 2021. A set of data items was defined along the following five axes: publication metadata, application scope, provenance aspects covered, data representation, and functionalities. The data items were extracted from the articles, stored in a charting spreadsheet, and summarized in tables and figures. We identified 44 original articles published between 2010 and 2021. We found that the solutions described were heterogeneous along all axes. We also identified relationships among motivations for the use of provenance information, feature sets (capture, storage, retrieval, visualization, and analysis), and implementation details such as the data models and technologies used. The important gap that we identified is that only a few publications address the analysis of provenance data or use established provenance standards, such as PROV. The heterogeneity of provenance methods, models, and implementations found in the literature points to the lack of a unified understanding of provenance concepts for biomedical data. Providing a common framework, a biomedical reference, and benchmarking data sets could foster the development of more comprehensive provenance solutions.

Assessment of the Coefficient of Tension in the Labor Market. Regional Aspect

.Assessing the situation in the labor market of the region, and ultimately forecasting the level of employment and unemployment, is a complex multidimensional mathematical problem that does not have a reliable and proven solution to date. Research in the direction of creating evaluation methods and forecasting the situation on the labor market is an actual task. The subject of the work is an assessment of the situation on the labor market of the Volga Federal District, through the analysis and modeling of the coefficient of tension in the labor market. The purpose of the study was to develop a methodology that allows making a preliminary forecast of the situation on the labor market of the subject of the Volga Federal District. The information base of the study was the results of a sample survey of the labor force conducted by state statistics bodies in accordance with the classifier of objects of administrative-territorial division (OKATO – Russian Classification on Objects of Administrative Division). To date, the length of the time series is four time periods (2018–2021) of the year. As methods of analysis and modeling, methods of descriptive statistics were used, as well as mathematical modeling of the relationship between the coefficient of tension in the labor market and the rating index of the socio-economic situation of the Volga Federal District. It is shown that the statistical grouping of the coefficient of tension in the labor market as a whole for all subjects of the Russian Federation is extremely heterogeneous, which makes it difficult to model processes in the labor market. At the same time, the statistical grouping of the coefficient of tension in the labor market of the regions of the Volga Federal District is quite homogeneous, which makes it possible to carry out simulations using such an integral index as the rating of the socio-economic situation of the subject of the Volga Federal District. In the process of modeling in the environment of the SPSS computer program, a nonlinear regression model of the relationship between the coefficient of tension in the labor market (dependent variable) and the place in the rating of the socio-economic situation of the subject of the Volga Federal District (explanatory variable) was formed. The model allows you to make a preliminary forecast of the situation on the labor market of the subject of the Volga Federal District.

Provenance-Preserving Analysis and Rewrite of Quantum Workflows for Hybrid Quantum Algorithms

Quantum applications are hybrid, i.e., they comprise quantum and classical programs, which must be orchestrated. Workflows are a proven solution for orchestrating heterogeneous programs while providing benefits, such as robustness or scalability. However, the orchestration using workflows can be inefficient for some quantum algorithms, requiring the execution of quantum and classical programs in a loop. Hybrid runtimes are offered to efficiently execute these algorithms. For this, the quantum and classical programs are combined in a single hybrid program, for which the execution is optimized. However, this leads to a conceptual gap between the modeling benefits of workflow technologies, e.g., modularization, reuse, and understandability, and the efficiency improvements when using hybrid runtimes. To close this gap, we introduce a method to model all tasks explicitly in the workflow model and analyze the workflow to detect parts of the workflow that can benefit from hybrid runtimes. Furthermore, corresponding hybrid programs are automatically generated based on the quantum and classical programs, and the workflow is rewritten to invoke them. To ease the live monitoring and later analysis of workflow executions, we integrate process views into our method and collect related provenance data. Thus, the user can visualize and monitor the workflow in the original and rewritten form within the workflow engine. The practical feasibility of our approach is validated by a prototypical implementation, a case study, and a runtime evaluation.

Specificity of 3D Printing and AI-Based Optimization of Medical Devices Using the Example of a Group of Exoskeletons

Three-dimensional-printed medical devices are a separate group of medical devices necessary for the development of personalized medicine. The present article discusses a modern and specific group of medical devices and exoskeletons, which aims to present our own experiences in the selection of materials, design, artificial-intelligence optimization, production, and testing of several generations of various upper limb exoskeletons when considering the Medical Devices Regulation (MDR) and the ISO 13485 and ISO 10993 standards. Work is underway to maintain the methodological rigor inherent in medical devices and to develop new business models to achieve cost-effectiveness so that inadequate legislation does not stop the development of this group of technologies (3D scanning, 3D printing, and reverse engineering) in the healthcare system. The gap between research and engineering practice and clinical 3D printing should be bridged as quickly and as carefully as possible. This measure will ensure the transfer of proven solutions into clinical practice. The growing maturity of 3D printing technology will increasingly impact everyday clinical practice, so it is necessary to prepare medical specialists and strategic and organizational changes to realize the correct implementation based on the needs of patients and clinicians.

Методологические инструменты управления орошением с искусственным интеллектом

Purpose: to develop the concept of irrigation management systems using integrated artificial intelligence technologies. Materials and methods. The working hypothesis of the research was the assumption of the priority of the cluster application of artificial intelligence technologies in solving urgent problems of irrigation management. At the same time, the basis of the information-computing unit of the irrigation control system should be deterministic algorithms using proven solutions. Results. Within the framework of the proposed concept, a neural network can be used as the basis for solving a problem, or it can only be used to adapt the parameters of the models used. The impact points of traditional, deterministic - analytical irrigation management systems and artificial intelligence technologies are determined by the need to adapt parameters, fine-tune the coefficients of the methodological tools used. At the same time, the scope of application of artificial intelligence in solving problems of irrigation management is quite wide. Artificial intelligence technologies can be used to solve the problems of irrigation planning and operational management, image recognition in satellite monitoring of soil moisture, interpolation of soil moisture data by area, forecasting the soil moisture profile. An algorithm using artificial intelligence technologies to improve the reliability of forecasting the total water consumption of irrigated crops in the regional and landscape aspect is developed by research. The proposed algorithm allows the system to self-learn and refine the regional values of bioclimatic coefficients, with respect to cumulative influence of local factors. Conclusions: a concept has been developed and new scientific approaches have been proposed to effectively solve the problem of adapting the parameters of methodological irrigation management tools at the level of an irrigated field, and even taking into account intra-field variability.

ANALYSIS AND EVALUATION OF BIOMETRIC AUTHENTICATION MEANS BASED ON THE IMAGE OF THE FACE AND IRIS OF THE STAFF OF CRITICAL INFRASTRUCTURE FACILITIES

Dedicated to the analysis and evaluation of biometric authentication systems for personnel of critical infrastructure facilities. It is shown that tools based on the image of the face and the iris of the eye have broad prospects, which is explained by the proven solutions in the field of face image analysis, the availability and distribution of video recording tools that allow the iris to be recorded simultaneously with the face with satisfactory quality. It was determined that one of the ways to improve the effectiveness of such tools is to increase the accuracy of face recognition and resistance to obstacles that cover part of the face. It is also shown that an additional direction of improving the effectiveness of biometrics can be recognition of the current psycho-emotional state of personnel of critical infrastructure facilities. The need to evaluate the effectiveness of face and emotion recognition tools based on face and iris images is determined. Based on the analysis of the literature, two groups of efficiency criteria were formed: basic and additional. Criteria characterizing the effectiveness of the recognition process are included in the main group, and criteria corresponding to the technical implementation features and service capabilities of recognition tools are included in the additional group. An evaluation of modern means of face and emotion recognition based on the image of the face and iris of the eye was carried out, and their non-compliance with a number of criteria was determined. It is proposed to correlate the ways of further research with the solution of the task of ensuring the fulfillment of the criteria related to the possibility of recognizing emotions and a person based on part of the image of the face, facial expressions and part of the image of the iris of the eye, with the technical implementation of expert solutions. The possibility of performing the specified task due to the use of modern neural network technologies is shown.

Unveiling Roadblocks and Mapping Solutions for Blockchain Adoption by Governments: A Systematic Literature Review

Aim/Purpose: Blockchain technology (BCT) has emerged as a potential catalyst for transforming government institutions and services, yet the adoption of blockchain in governments faces various challenges, for which previous studies have yet to provide practical solutions. Background: This study aims to identify and analyse barriers, potential solutions, and their relations in implementing BC for governments through a systematic literature review (SLR). The authors grouped the challenges based on the Technology-Organisation-Environment (TOE) framework while exercising a thematic grouping for the solutions, followed by a comprehensive mapping to unveil the relationship between challenges and solutions. Methodology: This study employs the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 methodology, combined with the tollgate method, to improve the quality of selected articles. The authors further administer a three-level approach (open coding, axial coding, and selective coding) to analyse the challenges and solutions from the articles. Contribution: The authors argue that this study enriches the existing literature on BC adoption, particularly in the government context, by providing a comprehensive framework to analyse and address the unique challenges and solutions, thus contributing to the development of new theories and models for future research in BC adoption in government settings and fostering deeper exploration in the field. Findings: The authors have unveiled 40 adoption challenges categorised using the TOE framework. The most prevalent technological challenges include security concerns and integration & interoperability, while cultural resistance, lack of support and involvement, and employees’ capability hinder adoption at the organisational level. Notably, the environmental dimension lacks legal and standard frameworks. The study further unveils 28 potential solutions, encompassing legal frameworks, security and privacy measures, collaboration and governance, technological readiness and infrastructure, and strategic planning and adoption. The authors of the study have further mapped the solutions to the identified challenges, revealing that the establishment of legal frameworks stands out as the most comprehensive solution. Recommendations for Practitioners: Our findings provide a big picture regarding BC adoption for governments around the globe. This study charts the problems commonly encountered by government agencies and presents proven solutions in their wake. The authors endeavour practitioners, particularly those in governments, to embrace our findings as the cornerstone of BC/BCT adoption. These insights can aid practitioners in identifying existing or potential obstacles in adopting BC, pinpointing success factors, and formulating strategies tailored to their organisations. Recommendation for Researchers: Researchers could extend this study by making an in-depth analysis of challenges or solutions in specific types of countries, such as developed and developing countries, as the authors believe this approach would yield more insights. Researchers could also test, validate, and verify the mapping in this study to improve the quality of the study further and thus can be a great aid for governments to adopt BC/BCT fully. Impact on Society: This study provides a comprehensive exploration of BC adoption in the government context, offering detailed explanations and valuable insights that hold significant value for government policymakers and decision-makers, serving as a bedrock for successful implementation by addressing roadblocks and emphasising the importance of establishing a supportive culture and structure, engaging stakeholders, and addressing security and privacy concerns, ultimately enhancing the efficiency and effectiveness of BC adoption in government institutions and services. Future Research: Future research should address the limitations identified in this study by expanding the scope of the literature search to include previously inaccessible sources and exploring alternative frameworks to capture dynamic changes and contextual factors in BC adoption. Additionally, rigorous scrutiny, review, and testing are essential to establish the practical and theoretical validity of the identified solutions, while in-depth analyses of country-specific and regional challenges will provide valuable insights into the unique considerations faced by different governments.

OPERA: Optional Dimensional Privacy-Preserving Data Aggregation for Smart Healthcare Systems

Massive multidimensional health data collected from Internet of Things (IoT) devices are driving a new era of smart health, and with it come privacy concerns. Privacy-preserving data aggregation (PDA) is a proven solution providing statistics while hiding raw data. However, existing PDA schemes ignore the willingness of data owners to share, so data owners may refuse to share data. To increase their willingness to contribute data, we propose an OPtional dimEnsional pRivacy-preserving data Aggregation scheme <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">(OPERA)</i> to provide data contributors with options on sharing dimensions while keeping their choices and data private. OPERA uses selection vectors to represent the decisions of users and count participants dimensionally and achieves data privacy and utility based on a multisecret sharing method and symmetric homomorphic cryptography. Analyses show that in OPERA, the probability of adversaries breaching privacy is less than 4.68e-97. Performance evaluations demonstrate that OPERA is outstanding in computation and practical in communication.

Towards more reproducible and FAIRer research data: documenting provenance during data acquisition using the Infofile format

Documenting data during their acquisition is an essential aspect of science, though rarely done well. The Infofile format is a simple, powerful and proven solution minimising overhead and thus enhancing reproducibility and quality of science.

Capturing Provenance from Deep Learning Applications Using Keras-Prov and Colab: a Practical Approach

Due to the exploratory nature of DNNs, DL specialists often need to modify the input dataset, change a filter when preprocessing input data, or fine-tune the models’ hyperparameters, while analyzing the evolution of the training. However, the specialist may lose track of what hyperparameter configurations have been used and tuned if these data are not properly registered. Thus, these configurations must be tracked and made available for the user’s analysis. One way of doing this is to use provenance data derivation traces to help the hyperparameter’s fine-tuning by providing a global data picture with clear dependencies. Current provenance solutions present provenance data disconnected from W3C PROV recommendation, which is difficult to reproduce and compare to other provenance data. To help with these challenges, we present Keras-Prov, an extension to the Keras deep learning library to collect provenance data compliant with PROV. To show the flexibility of Keras-Prov, we extend a previous Keras-Prov demonstration paper with larger experiments using GPUs with the help of Google Colab. Despite the challenges of running a DBMS with virtual environments, DL analysis with provenance has added trust and persistence in databases and PROV serializations. Experiments show Keras-Prov data analysis, during training execution, to support hyperparameter fine-tuning decisions, favoring the comparison, and reproducibility of such DL experiments. Keras-Prov is open source and can be downloaded from https://github.com/dbpina/keras-prov.

ENZYMES AND APPROACHES TO THEIR APPLICATION IN THE LEATHER PRODUCTION

In a market economy, the leather industry faces new challenges, including the need to improve and optimize technological processes to achieve the required quality of final products and comply with environmental legislation. The practical experience and long-term achievements of the authors in the field of natural leather production indicate the importance of choosing the right method and materials for processing raw and semi-finished hides. One proven solution is the use of enzymes. Based on the results of the analysis of literary sources, information on traditional ideas about enzymes and approaches to their use in the production of natural leather is systematized. According to established ideas, enzymes are not just organic substances, proteins, but also high-speed catalysts for multiple chemical and biochemical reactions. Preparations based on enzymes have been commercially studied in detergents, food, light, pharmaceutical, diagnostic, chemical and other industries, in the agro-industrial complex. This prevalence is explained by the fact that the use of these funds contributes to improving the quality of products, culture and the level of greening of production, more rational use of raw materials and material resources. In the leather industry, enzymatic processes have gone through a long evolutionary path – from the use of primitive improvised means to the use of preparations that are more up to date with the requirements of the time. According to the modern classification, enzymes are divided into six main classes according to the nature of the catalyzed reaction. In the manufacture of genuine leather, taking into account the nature of the substrate (proteins, carbohydrates, lipids), preparations based on enzymes are used that belong to the class of hydrolases (proteases, amylases, lipases) and differ from each other in the active center and mode of action. The preparations used can either accelerate processes that usually proceed slowly (soaking), or provide a specific transformation of raw material (bating), or replace known chemical reagents (unhairing). The results obtained will be taken into account in the future when studying innovative approaches to the enzymization of leather production.