Publications Repository - Gdańsk University of Technology

Page settings

polski
Publications Repository
Gdańsk University of Technology

Show publications from the year

Publications from the year 2024

Show all
  • Impact of spraying commercial Bentonite Nanoclay on fortification of the mortar as Nano Sprying Technique (NST) in heritages and historical buildings
    • Saeideh Jalalifar
    • Hamed Niroumand
    • Maryam Afsharpour
    • Shadi Rajabi
    • Lech Bałachowski
    2024 Full text Scientific Reports

    Spraying Bentonite NanoClay as an innovative idea satisfied an urgent need for conservation of historical brick constructions. This research explores the application of Nanotechnology as a Nano-Geotechnics (NaG) and Nano Ground Improvement (NGI) techniques for fortifying the mortar between bricks in historical buildings against some environmental erosive factors. Bentonite Nanoparticles were selected because of their compatibility with mortar. They were applied via Nano Spray to mitigate holes and cracks caused by erosion. Various percentages of bentonite NanoClay (2–10%) Spray and the number of times to spray on the mortar were evaluated. Validation through field emission scanning electron microscopy imaging (FESEM/SEM), X-Ray differaction and Fluorescence analyses (XRD/XRF), Inductively coupled plasma optical emission spectroscopy (ICP-OES), Brunauer–Emmett–Teller (BET), porosity tests, water absorption time measurement, and weathering tests confirmed the efficacy and long-term stability of this method. The result indicated that double spraying of a 2% NanoClay solution proved most effective in reducing porosity, declining water absorption, and enhancing resistance to freezing and rain.

  • Impact of the Kanban Maturity Model on a Team’s Agile Transformation: Tripling Throughput and Elevating Quality in Three Months
    • Jacek Trzesicki
    • Krzysztof Marek
    • Adam Przybyłek
    2024

    Agile transformations have been a significant challenge since the beginning of the agile movement, with numerous researchers and practitioners suggesting various structured approaches and guidelines. The Kanban Maturity Model (KMM) is a relatively new approach that focuses on assessing the current maturity level of an organisation, with an emphasis on a spectrum of Kanban practices. This paper presents the initial results of applying the KMM as a guide for subsequent steps in Kanban implementation and agile transformation. The exploratory case study describes the application of the KMM in the agile transformation of a software development team within a midsize organisation. Despite previous unsuccessful attempts to implement Scrum, the adoption of KMM facilitated a rapid and successful implementation of the Kanban Method. Within three months, the team’s throughput tripled, and the quality of the developed software improved significantly. The results suggest that the KMM can be successfully used as an effective guideline for agile transformation of software development teams.

  • Impact of the type of heat exchanger on the characteristics of low-temperature thermoacoustic heat engines
    • Volodymyr Korobko
    • Anatoliy Shevtsov
    • Serhiy Serbin
    • Huabing Wen
    • Marek Dzida
    2024 International Journal of Thermofluids

    Thermoacoustic technologies are considered an effective solution for harnessing low-temperature heat, whether from waste or renewable sources. However, in practice, developing and implementing high-performance ther- moacoustic systems is a complex challenge. In real waste heat recovery systems, heat exchange between ther- moacoustic engines (TAEs) and external heat sources is facilitated by auxiliary systems, such as circulation loops that include recuperative heat exchangers. It is evident that the upper power limit of a TAE is constrained by the thermal performance of its internal heat exchangers. This article investigates the energy transfer processes be- tween the internal recuperative heat exchangers of a TAE and its matrix, and presents a mathematical model describing the interactions between the matrix and the heat exchangers. The model accounts for the effects of temperature inhomogeneities on the surface of the recuperative heat exchangers, which influence the temper- ature distribution within the TAE matrix. The use of liquid-gas recuperative heat exchangers in TAEs introduces temperature heterogeneity within the components of the thermoacoustic core. This study shows that such temperature variations can reduce the matrix gain factor for additional acoustic energy by a factor of 1.1 to 1.3. Therefore, when designing low-temperature thermoacoustic systems, it is essential to consider the type and characteristics of the heat exchangers used. The analysis indicates that recuperative heat exchangers can reduce the efficiency of thermoacoustic machines, whether they function as engines or refrigerators.

  • Impact of trajectory simplification methods on modeling carbon dioxide emissions from ships
    • Tadeusz Balcer
    • Rafał Szłapczyński
    • Thomas Mestl
    2024 OCEAN ENGINEERING

    Models of ship fuel consumption and emissions play an essential role in estimating global shipping’s greenhouse gas emissions. They are also widely used for verification of reported CO2 emissions for systems like EU MRV (Monitoring, Reporting and Verification) or IMO DCS (Data Collection System). Such models achieve high accuracy using historical spatiotemporal information about each ship from AIS data. However, this approach requires substantial computing capacity. To reduce the computational load, trajectory simplification algorithms are frequently applied. In this work, we evaluate their impact on CO2 estimations by comparing various trajectory simplification methods, including Fixed Time Downsampling, Douglas-Peucker, Top-Down Time Ratio and Optimized Equivalent Passage Plan. Through simulation and a random selection of real ship trajectories we demonstrate that by choosing the right method both, the amount of data as well the computation time can be significantly reduced while maintaining acceptable estimations of CO2 emissions.

  • Impact of Visual Image Quality on Lymphocyte Detection Using YOLOv5 and RetinaNet Algorithms
    • Agata Polejowska
    • Milena Sobotka
    • Michał Kalinowski
    • Marcin Kordowski
    • Tomasz Neumann
    2024

    Lymphocytes, a type of leukocytes, play a vital role in the immune system. The precise quantification, spatial arrangement and phenotypic characterization of lymphocytes within haematological or histopathological images can serve as a diagnostic indicator of a particular lesion. Artificial neural networks, employed for the detection of lymphocytes, not only can provide support to the work of histopathologists but also enable better disease monitoring and faster analysis of the general immune system condition. In this study, the impact of visual quality on the performance of state-of-the-art algorithms for detecting lymphocytes in medical images was examined. Two datasets were used, and image modifications such as blur, sharpness, brightness, and contrast were applied to assess the performance of YOLOv5 and RetinaNet models. The study revealed that the visual quality of images exerts a substantial impact on the effectiveness of the deep learning methods in detecting lymphocytes accurately. These findings have significant implications for deep learning approaches used in digital pathology.

  • Impact of Work from Home on Agile Software Project Execution – the Empirical Study
    • Jakub Chabik
    2024 Full text

    Background: The outbreak of a Covid-19 pandemic changed the working patterns of software projects delivery. Aim: The study examines how the work from home (WFH) impacted the software project execution for emergence of differentiating patterns. Method: The data on project execution in two country locations was examined. The population is 3711 projects across 52 months (26 pre- and 26 post-pandemic) is analyzed. The paper identifies the changed patterns of execution. Results: WFH resulted in a more frequent reporting of the project status, significantly higher granularity of reporting, small changes in the statuses reported and significant changes in the duration of a project in a given status. Conclusion: The study concludes that the WFH have had overall positive impact on the software project execution, but notices that it was achieved with increase in reporting frequency and granularity. Keywords:software engineering, project management, empirical study, data-driven software engineering.

  • Impacts of Using Exhaust Gas Recirculation and Various Amount of Dimethyl Ether Premixed Ratios on Combustion and Emissions on a Dual-Fuel Compression Ignition Engine
    • Denys Stepanenko
    • Jacek Rudnicki
    • Zbigniew Kneba
    2024 Full text Advances in Science and Technology Research Journal

    In the presented research, the authors dealt with the specific properties of the combustion process of dimethyl ether (DME) in a combustion car (Volkswagen Golf IV) engine AJM 1.9 TDI PDE made by Volkswagen factory. Dimethyl ether is an alternative fuel produced most often from natural gas, which can be used in compression ignition engines as a single fuel or co-burned with diesel oil. This work describes the impacts of using exhaust gas recirculation (EGR) system and various diesel to DME substitution ratios from 0% to approximately 25% (on an energy basis), on the combustion process in a dual-fuel diesel engine. The engine has been modified so that DME fuel is introduced into the intake manifold just before the intake valves. The diesel fuel supply system, operation algorithms of the engine electronic control unit and other engine elements were left unchanged as it was built by the manufacturer.

  • Implementing fermentation technology for comprehensive valorisation of seafood processing by-products: A critical review on recovering valuable nutrients and enhancing utilisation
    • Shahida Anusha Siddiqui
    • Dhanya Lakshmikanth
    • Chiranjiv Pradhan
    • Zahra Farajinejad
    • Roberto Castro Munoz
    • Abhilash Sasidharan
    2024 Full text CRITICAL REVIEWS IN FOOD SCIENCE AND NUTRITION

    Fermentation technology is a biorefining tool that has been used in various industrial processes to recover valuable nutrients from different side streams. One promising application of this technique is in the reclamation of nutritional components from seafood side streams. Seafood processing generates significant amounts of waste, including heads, shells, and other side streams. These side streams contain high quantities of valued nutritional components that can be extracted using fermentation technology. The fermentation technology engages the application of microorganisms to convert the side stream into valuable products like biofuels, enzymes, and animal feed. Natural polymers such as chitin and chitosan have various purposes in the food, medicinal, and agricultural industry. Another example is the fish protein hydrolysates (FPH) from seafood side streams. FPHs are protein-rich powders which could be used in animal nutrition and nutraceutical industry. The resulting hydrolysate is further filtered and dried resulting in a FPH powder. Fermentation technology holds great possibility in the recovery of valuable nutrients from seafood side streams. The process can help reduce waste and generate new value-added products from what would otherwise be considered a waste product. With further research and development, fermentation technology can become a key tool in the biorefining industry.

  • Importance of artificial intelligence to support the process of anaerobicdigestion of kitchen waste with bioplastics / Znaczenie sztucznej inteligencji we wspomaganiu procesu beztlenowej fermentacji odpadów kuchennych zawierających bioplastiki
    • Ryszard Arendt
    • Andrzej Kopczyński
    • Jan Hupka
    • Aleksandra Grabowiec
    2024 Full text Przemysł Chemiczny

    Artificial intelligence (AI) and machine learning were used to obtain more effective methods for conducting the digestion process and achieving final products. Data acquisition was carried out by an automatic monitoring and anal. research. The knowledge describing the anaerobic digestion process was summarized in the form of rules: IF (premise) THEN (conclusion). The compiled set of rules created a knowledge base of the expert system, which was used to run the anaerobic digestion process and provided instructions to the operator. Knowledge rules were updated and developed during the process. The construction of a mobile laboratory system for the anaerobic digestion of kitchen and food waste, the tech. devices, the structure of the AI system, and selected knowledge rules were presented.

  • Importance of sign conventions on analytical solutions to the wave-induced cyclic response of a poro-elastic seabed
    • Waldemar Magda
    2024 Full text Archives of Civil Engineering

    This paper discusses the influence of different sign conventions for strains and stresses, i.e. the solid mechanics sign convention and the soil mechanics sign convention, on the form of governing partial differential equations (the static equilibrium equations and the continuity equation) used to describe the wave-induced cyclic response of a poro-elastic seabed due to propagation of a sinusoidal surface water-wave. Some selected analytical solutions, obtained by different authors and published in specialist literature in the form of complex functions describing the wave-induced pore-fluid pressure, effective normal stress and shear stress oscillations in the seabed, have been analysed and compared with each other mainly with respect to different sign conventions for stains and stresses and also with regard to different orientations of the positive vertical axis of the two-dimensional coordinate system and different directions of surface water-wave propagation. The performed analyses of the analytical solutions has indicated many inaccuracies, or even evident errors and exemplary mistakes of wrong-signed values of basic wave-induced response parameters (the shear stress in particular), thereby disqualifying these solutions and their final equations from practical engineering applications. Most of the mistakes found in the literature must be linked to authors’ lack of understanding and consistency in an uniform application of a certain sign convention for strains and stresses in the soil matrix at both stages of mathematical formulation of the governing problem and correct interpretation of equations of the final analytical solution. The present paper, based mostly on a thorough literature review, ought to draw attention and arouse interest among coastal scientists and engineers in proper identification and use of the existing analytical solutions to the wave-induced cyclic seabed response – solutions which differ very often in the applied sign convention for stresses in the soil matrix.

  • Improved Bandwidth of Microstrip Wide-Slot Antenna Using Gielis Curves
    • Davood Zarifi
    • Ali Farahbakhsh
    • Michał Mrozowski
    2024 IEEE Access

    The development of a broadband printed wide-slot antenna based on Gielis curves is presented in this article. The printed wide-slot antenna can be conveniently reshaped to achieve ultra-wideband performance by using superformula. The distinct advantage of employing the superformula in design of wide-slot antenna lies in its ability to define nearly any geometric shape including non-standard, complex and non-intuitive for the wide-slot and by finely tuning just six parameters. To demonstrate the capabilities of the proposed approach, a simple prototype is fabricated and tested. The satisfactory correspondence between the measurement and the simulation results confirms the effectiveness of the antenna being proposed. The experimental findings reveal that the antenna’s impedance bandwidth, where the VSWR is less than 2, spans from 2 to 13.9 GHz, encompassing a range that is 150% wide. Furthermore, the antenna demonstrates a realized gain ranging between 3.8 to 6.4 dBi within its operational frequency spectrum. These results indicate that the antenna exhibits the efficiency and functionality required for application in wideband communication systems

  • Improved Efficacy Behavioral Modeling of Microwave Circuits through Dimensionality Reduction and Fast Global Sensitivity Analysis
    • Sławomir Kozieł
    • Anna Pietrenko-Dąbrowska
    • Leifur Leifsson
    2024 Full text Scientific Reports

    Behavioral models have garnered significant interest in the realm of high-frequency electronics. Their primary function is to substitute costly computational tools, notably electromagnetic (EM) analysis, for repetitive evaluations of the structure under consideration. These evaluations are often necessary for tasks like parameter tuning, statistical analysis, or multi-criterial design. However, constructing reliable surrogate models faces several challenges, including the nonlinearity of circuit characteristics and the vast size of the parameter space, encompassing both dimensionality and design variable ranges. Additionally, ensuring the validity of the model across broad geometry/material parameter and frequency ranges is crucial for its utility in design. The purpose of this paper is to introduce an innovative approach to cost-effective and dependable behavioral modeling of microwave passives. Central to our method is a fast global sensitivity analysis (FGSA) procedure, which is devised to identify correlations between design parameters and quantify their impacts on circuit characteristics. The most significant directions identified through FGSA are utilized to establish a reduced-dimensionality domain. Within this domain, the model may be constructed using a limited amount of data samples while capturing a significant portion of the circuit response variability, rendering it suitable for design purposes. The outstanding predictive capability of the proposed model, its superiority over traditional techniques, and its readiness for design applications are demonstrated through the analysis of three microstrip circuits of diverse characteristics.

  • Improved maximum power point tracking algorithms by using numerical analysis techniques for photovoltaic systems
    • Lyu Guanghua
    • Syed M. Hussain
    • Arsalan Muhammad Soomar
    • Shoaib Shaikh
    • Syed Hadi Hussain Shah
    2024 Full text Results in Engineering

    Solar photovoltaic (PV) panels generate optimal electricity when operating at the maximum power point (MPP). This study introduces a novel MPP tracking algorithm that leverages the numerical prowess of the predictor-corrector method, tailored to accommodate voltage and current fluctuations in PV panels resulting from variable environmental factors like solar irradiation and temperature. This paper delves into the intricate dynamics of solar panels, presenting a comprehensive mathematical model capturing the interdependencies between current, voltage, power, solar irradiation, and temperature. Existing numerical MPPT techniques are explored to provide their advantages and disadvantages. The proposed algorithm, formulated in MATLAB, encapsulates essential solar panel variables and undergoes rigorous dynamic testing in the Simulink® environment under diverse solar irradiation and temperature scenarios. These results are visually represented through graphs and tabulations. A subsequent section offers a simulation-driven comparative review of the proposed algorithm against established methodologies. The article culminates with conclusions drawn from the empirical findings and outlines promising avenues for future research.

  • Improving in-situ biomethanation of sewage sludge under mesophilic conditions: Performance and microbial community analysis
    • Mohamed S. Hellal
    • Filip Gamoń
    • Grzegorz Cema
    • Kishore Kumar Kadimpati
    • Aleksandra Ziembińska-Buczyńska
    • Joanna Surmacz-Górska
    2024 BIOMASS & BIOENERGY

    This research investigated the application of in-situ biological hydrogen methanation within a continuous stirred tank reactor (CSTR) system under mesophilic conditions, with sewage sludge used as the substrate. Two CSTRs with an effective capacity of 5 L were installed and loaded with inoculum sludge with a volatile solid (VS) concentration of 1.2–1.5 %. They were fed mixed waste sludge with an organic loading rate (OLR) of 1.5 g VS/L and an average sludge retention time (SRT) of 19 days under mesophilic conditions at 37 ◦C. One of the reactors operated as a control, while the other was injected with H2 through a microceramic membrane diffuser with a H2: CO2 ratio of 4:1. The results of this study revealed that the addition of H2 and the recirculation of residual hydrogen in biogas led to a substantial increase in the production of methane from 157 L/kg VS to 275 L/kg VS. Increasing the methane content in biogas from 52 % to 78 % yielded an impressive 42.8 % higher methane production rate. Metataxonomic analysis of the microbial community via high-throughput sequencing tech- niques revealed that the dominant acetoclastic and hydrogenotrophic methanogens were Methanosaeta and Methanoregula, respectively, with greater abundances of both groups in the experimental bioreactor. The dy- namics of their activity in both bioreactors were analyzed via qPCR, and the functional genes encoding methyl- coenzyme M reductase (mcrA gene) and hydrogenase Ni-Fe presented comparable changes between RI and RII. By optimizing key operational parameters and closely examining the dynamics of the microbial community, this approach can contribute significantly to sustainable bioenergy solutions while minimizing environmental impact.

  • Improving Output Performance of the Ultrasonic Multicell Piezoelectric Motor by Development the Multi-Rotor Structure
    • Roland Ryndzionek
    2024 Full text IEEE Access

    In recent years, many researches have been carried out on piezoelectric multi-rotor structures. This paper describes the analysis, development and experimental process of an ultrasonic multi-cell piezoelectric motor using a multi-rotor structure. In this design, three independent cells have been integrated into a mechatronic system. Analytical model and finite element method are used for modal and dynamic analysis of the proposed motor. The multicell motor prototype has been manufactured and tested in the laboratory. Finally, the results of analytical, simulations and experimental investigation have been compared. The compared results are in satisfactory agreement. The measured parameters were: resonance frequency characteristics, mechanical characteristics of the single actuator and the complete assembled motor. The maximum speed and load of the motor have been determined. The maximum speed of 512 rpm was obtained with a voltage of 86 Vrms and the maximum stall torque was 120 mNm. Finally, the multi-rotor structure was compared with other rotary ultrasonic structures.

  • Improving platelet‐RNA‐based diagnostics: a comparative analysis of machine learning models for cancer detection and multiclass classification
    • Maksym Albin Jopek
    • Krzysztof Pastuszak
    • Michał Sieczczyński
    • Sebastian Cygert
    • Anna J. Żaczek
    • Matthew T. Rondina
    • Anna Supernat
    2024 Full text Molecular Oncology

    Liquid biopsy demonstrates excellent potential in patient management by providing a minimally invasive and cost-effective approach to detecting and monitoring cancer, even at its early stages. Due to the complexity of liquid biopsy data, machine-learning techniques are increasingly gaining attention in sample analysis, especially for multidimensional data such as RNA expression profiles. Yet, there is no agreement in the community on which methods are the most effective or how to process the data. To circumvent this, we performed a large-scale study using various machine-learning techniques. First, we took a closer look at existing datasets and filtered out some patients to assert data collection quality. The final data collection included platelet RNA samples acquired from 1397 cancer patients (17 types of cancer) and 354 asymptomatic, presumed healthy, donors. Then, we assessed an array of different machine-learning models and techniques (e.g., feature selection of RNA transcripts) in pan-cancer detection and multiclass classification. Our results show that simple logistic regression performs the best, reaching a 68% cancer detection rate at a 99% specificity level, and multiclass classification accuracy of 79.38% when distinguishing between five cancer types. In summary, by revisiting classical machine-learning models, we have exceeded the previously used method by 5% and 9.65% in cancer detection and multiclass classification, respectively. To ease further research, we open-source our code and data processing pipelines (https://gitlab.com/jopekmaksym/improving-platelet-rna-based-diagnostics), which we hope will serve the community as a strong baseline.

  • Improving Social Justice, Environmental Integrity, and Geopolitical Resilience in EU Electric Mobility Transition
    • Aleksandra Lis-Plesińska
    • Nathalie Ortar
    • Rafał Szymanowski
    • Marek Jaskólski
    • Aleksandra Parteka
    • Christine Buisson
    2024

    We recommend improving social justice, environmental integrity, and geopolitical resilience in electric mobility transition. To achieve this policy recommendation, we propose the following: (1) Increase societal acceptance and justice of climate policies by engaging local stakeholders; (2) Prioritize sustainable mobility practices over replacement of internal combustion engine vehicle (ICEV) with battery electric vehicle (BEV); (3) Base resilience of global value and supply chains on a diversified network of suppliers and a balanced structure of domestic and foreign content of economic value; (4) Evaluate geo-political risks and environmental impacts of value and supply chains in non-European regions; (5) Create a geopolitical risk body to scrutinise geopolitical threats to the electric mobility supply chain; and (6) Increase the share of EU-based manufacturing in electric mobility related sectors.

  • Improving the Efficiency of Semitransparent Perovskite Solar Cell Using Down-Conversion Coating
    • Damian Głowienka
    • Chieh-Ming Tsai
    • Aoussaj Sbai
    • Dian Luo
    • Pei-Huan Lee
    • Shih-Han Huang
    • Chia-Feng Li
    • Hao-Wen Wang
    • Guey-Sheng Liou
    • Julien Guthmuller
    • Wei-Fang Su
    2024 ACS Applied Materials & Interfaces

    Perovskite solar cells (PSCs) have demonstrated exceptional efficiency, yet surpassing theoretical performance limits requires innovative methodologies. Among these, down-conversion techniques are pivotal in reducing optical losses and enhancing energy conversion efficiency. In this study, optical modeling, including a generalized transfer-matrix optical model, was employed to meticulously assess optical losses in semitransparent PSCs illuminated from the front and rear sides of the device. To reduce these losses, two down-conversion layers, made of N,N-diphenyl-4-(1,2,2-triphenylethenyl)-benzenamine and 4-(N,Ndiphenylamino)benzaldehyde mixed with polymeric binder, were developed, showcasing initial photoluminescence quantum yields of 60% and 50% as films, respectively. The materials luminescence relies on the effect of aggregation-induced emission, which enhances the fluorescence of the dyes within the binder, providing their films with a unique behavior beneficial for photovoltaic applications. An optimization of these layers was performed, which aimed to reduce UV optical losses by adjusting the film thickness atop the PSCs. The refined down-conversion layers yielded a notable increase in the power conversion efficiency by approximately 0.4% for both the front and rear sides of the PSCs, demonstrating their significant potential in pushing the boundaries of solar cell performance

  • Improving the efficiency of street lighting electrical systems
    • O.m. Sinchuk
    • Tetiana Beridze
    • O.Yu. Mykhailenko
    • V. V Horshkov
    • M. V Rogoza
    • Ryszard Strzelecki
    2024 Scientific Bulletin of National Mining University [ Науковий вісник Національного гірничого університету ]

    To derive mathematical expressions that, using the available information, will allow forecasting the levels of electricity consumption by the city’s outdoor lighting network in the main possible scenarios for several years ahead, as well as when developing an energy-efficient smart control system for the electro-complex of lighting complex. Creating an effective intelligent outdoor lighting control system involves the use of the following methods. First, using the empirical measurement method, information on illumination, electricity consumption, car and pedestrian traffic is obtained. Statistical methods are used to identify patterns and relationships between the measured values, as well as to make subsequent forecasts. For intelligent control of outdoor lighting, a decision-making method based on fuzzy inference is used, which allows one, based on information about the operating conditions of the outdoor lighting network, to determine the recommended value of the current or value of lighting devices and the required power source. This approach will ensure maximum system efficiency. The obtained analytical dependencies for forecasting the electricity consumption, which are based on data from different time intervals, have determination coefficients of 66.8 and 88.1 %, respectively. The simulation of the operation of a fuzzy control system for the electricity consumption of outdoor lighting on the example of an operated part of the road operated and illuminated by ten 100 W LED lamps for summer and winter nights with different discrete control steps confirms the possibility of achieving the efficiency of outdoor lighting when using the proposed controllability option. The combined-powered control system is more efficient, reducing electricity consumption in summer and winter by more than 70 % compared to traditional schemes. A fuzzy control system for the electrical complex of outdoor lighting in cities is improved, which takes into account the electricity tariff in addition to the level of illumination and the car or pedestrian traffic when generating the control action for the LED driver and determining the rational power source (grid or grid/battery) for lighting devices. The architecture of the system for controlling electricity consumption by electrical receivers of lighting networks based on the fuzzy inference algorithm is developed, which is recommended for use to ensure an increase in the energy efficiency of this class of municipal consumers

  • Improving the prediction of biochar production from various biomass sources through the implementation of eXplainable machine learning approaches
    • Van Giao Nguyen
    • Prabhakar Sharma
    • Ümit Ağbulut
    • Huu Son Le
    • Dao Nam Cao
    • Marek Dzida
    • Sameh M. Osman
    • Huu Cuong Le
    • Viet Dung Tran
    2024 International Journal of Green Energy

    Examining the game-changing possibilities of explainable machine learning techniques, this study explores the fast-growing area of biochar production prediction. The paper demonstrates how recent advances in sensitivity analysis methodology, optimization of training hyperparameters, and state-of-the-art ensemble techniques have greatly simplified and enhanced the forecasting of biochar output and composition from various biomass sources. The study argues that white-box models, which are more open and comprehensible, are crucial for biochar prediction in light of the increasing suspicion of black-box models. Accurate forecasts are guaranteed by these explainable AI systems, which also give detailed explanations of the mechanisms generating the outcomes. For prediction models to gain confidence and for biochar production processes to enable informed decision-making, there must be an emphasis on interpretability and openness. The paper comprehensively synthesizes the most critical features of biochar prediction by a rigorous assessment of current literature and relies on the authors’ own experience. Explainable machine learning techniques encourage ecologically responsible decision-making by improving forecast accuracy and transparency. Biochar is positioned as a crucial participant in solving global concerns connected to soil health and climate change, and this ultimately contributes to the wider aims of environmental sustainability and renewable energy consumption.