Hasil untuk "Industrial safety. Industrial accident prevention"

Nicole White, Shannon L. Wagner

ABSTRACT Advancing workplace mental health prevention is paramount, yet to date there are no effective, evidence‐based strategies that can be widely recommended for prevention of occupational trauma‐related symptoms. Because the conceptual framework of prevention following potentially psychologically traumatic exposure (PPTE) is to intervene prior to the development or worsening of trauma‐related symptoms, an index of successful prevention is to observe no change or minimal change in baseline symptom levels. Considering common pitfalls of statistically interpreting an absence of change, in this review, we address the widespread problem of null findings in prevention science and discuss theoretical and analytical concepts to advance the quality and strength of inferences that can be drawn from statistical analysis in quantitative prevention science. Public safety personnel (PSP) comprise a unique set of occupational groups where frequent exposure to PPTEs is an inherent occupational hazard. Correspondingly, PSP demonstrate elevated prevalence rates of trauma‐related disorders including PTSD, depression, anxiety, sleep problems, and substance use, and development of effective, evidence‐based prevention is urgently needed. Using insights from research with PSP samples as a case study, we summarize current limitations constraining occupation‐related prevention science and offer an overview of research design and analytical strategies to promote the development and testing of rigorous and effective prevention strategies to support occupational mental health.

Rui Ma, Yifeng Wang, Ziteng Yang et al.

Visual analysis and reconstruction of pipeline inner walls remain challenging in industrial inspection scenarios. This paper presents a dedicated reconstruction system for pipeline inner walls via industrial endoscopes, which is built on panoramic image stitching technology. Equipped with a custom graphical user interface (GUI), the system extracts key frames from endoscope video footage, and integrates polar coordinate transformation with image stitching techniques to unwrap annular video frames of pipeline inner walls into planar panoramic images. Experimental results demonstrate that the proposed method enables efficient processing of industrial endoscope videos, and the generated panoramic stitched images preserve all detailed features of pipeline inner walls in their entirety. This provides intuitive and accurate visual support for defect detection and condition assessment of pipeline inner walls. In comparison with the traditional frame-by-frame video review method, the proposed approach significantly elevates the efficiency of pipeline inner wall reconstruction and exhibits considerable engineering application value.

Sourya Saha, Md. Nurul Absur

Extended Reality (XR) systems deployed in industrial and operational settings rely on Visual--Inertial Odometry (VIO) for continuous six-degree-of-freedom pose tracking, yet these environments often involve sensing conditions that deviate from ideal assumptions. Despite this, most VIO evaluations emphasize nominal sensor behavior, leaving the effects of sustained sensor degradation under operational conditions insufficiently understood. This paper presents a controlled empirical study of VIO behavior under degraded sensing, examining faults affecting visual and inertial modalities across a range of operating regimes. Through systematic fault injection and quantitative evaluation, we observe a pronounced asymmetry in fault impact where degradations affecting visual sensing typically lead to bounded pose errors on the order of centimeters, whereas degradations affecting inertial sensing can induce substantially larger trajectory deviations, in some cases reaching hundreds to thousands of meters. These observations motivate greater emphasis on inertial reliability in the evaluation and design of XR systems for real-life industrial settings.

Vladyslav Horhulenko

У статті викладено основні положення математичної моделі визначення ймовірнісних станів інформаційно-комунікаційної системи в умовах ведення відносно до неї кіберборотьби. Метою статті є розроблення математичної моделі визначення ймовірнісних станів інформаційно-комунікаційної системи в умовах ведення кіберборотьби як випадкового дифузійного марковського процесу. На відміну від існуючих, розроблена автором математична модель враховує ймовірнісний характер факторів, які впливають на перебіг та результати кіберборотьби, розглядає її як дифузійний випадковий марковський процес з дискретними станами та неперервним часом. Методи дослідження. Під час дослідження використано метод системного аналізу для визначення множини можливих станів інформаційно-комунікаційної системи, а також математичний апарат теорії стохастичних диференціальних рівнянь для аналітичного моделювання її функціонування. За допомогою методу системного аналізу було формалізовано процес кіберборотьби, проаналізовано трирівневу архітектуру кіберпростору (кібердомену) як середовища її ведення та сформовано множину можливих станів функціонування інформаційно-комунікаційної системи, що складається з шести станів. Математичний апарат теорії стохастичних диференціальних рівнянь дав змогу сформувати систему диференціальних рівнянь Колмогорова у стохастичній постановці для визначення ймовірностей станів інформаційно-комунікаційної системи. Отримані результати дослідження. У результаті дослідження було формалізовано процес ведення кіберборотьби у якості дифузійного марковського процесу з дискретними станами та неперервним часом, узагальнено за структурною ознакою основні об’єкти ведення кіберборотьби як інформаційно-комунікаційні системи, запропоновано граф станів функціонування такої системи та розроблено математичну модель визначення її ймовірнісних станів в умовах ведення кіберборотьби на основі математичного апарату теорії стохастичних диференціальних рівнянь. Елементи наукової новизини. Науковою новизною отриманих результатів дослідження є запропонований у статті концептуально інший підхід до оцінювання ефективності ведення кіберборотьби, який зводиться до її математичного моделювання як випадкового (стохастичного) процесу та отримання, завдяки цьому, саме ймовірнісних показників, за якими в подальшому буде можливо аналізувати величину прогнозованого ефекту від кібердій та використовувати в якості критеріїв прийняття рішення на їх проведення. Теоретична й практична значущість. Теоретичною значущістю отриманого наукового результату є прикладне використання потужного математичного апарату теорії стохастичних диференціальних рівнянь для аналітичного математичного моделювання дій у кіберпросторі, яким за означенням притаманна невизначеність та випадковість. Практичною значущістю результатів дослідження є можливість програмної реалізації запропонованої у статті математичної моделі визначення ймовірнісних станів інформаційно-комунікаційної системи для прогнозування перебігу та результатів ведення кіберборотьби в інтересах застосування угруповань військ (сил) оперативно-стратегічного рівня.

Clinton Manuel de Nascimento, Jin Hou

Intrusion detection systems (IDSs) must operate under severe class imbalance, evolving attack behavior, and the need for calibrated decisions that integrate smoothly with security operations. We propose a human-in-the-loop IDS that combines a convolutional neural network and a long short-term memory network (CNN–LSTM) classifier with a variational autoencoder (VAE)-seeded conditional Wasserstein generative adversarial network with gradient penalty (cWGAN-GP) augmentation and entropy-based abstention. Minority classes are reinforced offline via conditional generative adversarial (GAN) sampling, whereas high-entropy predictions are escalated for analysts and are incorporated into a curated retraining set. On CIC-IDS2017, the resulting framework delivered well-calibrated binary performance (ACC = 98.0%, DR = 96.6%, precision = 92.1%, F1 = 94.3%; baseline ECE ≈ 0.04, Brier ≈ 0.11) and substantially improved minority recall (e.g., Infiltration from 0% to >80%, Web Attack–XSS +25 pp, and DoS Slowhttptest +15 pp, for an overall +11 pp macro-recall gain). The deployed model remained lightweight (~42 MB, <10 ms per batch; ≈32 k flows/s on RTX-3050 Ti), and only approximately 1% of the flows were routed for human review. Extensive evaluation, including ROC/PR sweeps, reliability diagrams, cross-domain tests on CIC-IoT2023, and FGSM/PGD adversarial stress, highlights both the strengths and remaining limitations, notably residual errors on rare web attacks and limited IoT transfer. Overall, the framework provides a practical, calibrated, and extensible machine learning (ML) tier for modern IDS deployment and motivates future research on domain alignment and adversarial defense.

Bibish Chaulagain, Sanjeev Khanna

This study evaluates the techno-economic feasibility of supplying industrial thermal loads with green hydrogen produced via water electrolysis using two pathways off-grid systems powered by co-located wind turbines and battery energy storage (BESS), and on-grid systems that procure electricity directly from the wind farm power node and operate electrolysers in response to real-time locational marginal prices (LMPs).The optimization results show that off-grid wind-to-hydrogen configurations in high-resource regions can achieve levelized costs of hydrogen (LCOH) on the order of \$7/kg, driven by high wind capacity factors and optimized BESS sizing that ensures operational continuity .Similarly in, on-grid, price-responsive operation achieves LCOH values of \$0.5/kg, reflecting sensitivity to electricity market volatility. Overall, the results suggest that Midwest wind-rich regions can support competitive green hydrogen production for industrial heat, with grid-connected electrolysers remaining attractive in locations with frequent low LMP periods. This dual-path analysis provides a transparent framework for industrial hydrogen deployment and highlights practical transition strategies for decarbonizing U.S. manufacturing.

Sungmin Kang, Sumi Yun, Jingun Hong et al.

Fault Localization (FL) aims to identify root causes of program failures. FL typically targets failures observed from test executions, and as such, often involves dynamic analyses to improve accuracy, such as coverage profiling or mutation testing. However, for large industrial software, measuring coverage for every execution is prohibitively expensive, making the use of such techniques difficult. To address these issues and apply FL in an industrial setting, this paper proposes AutoCrashFL, an LLM agent for the localization of crashes that only requires the crashdump from the Program Under Test (PUT) and access to the repository of the corresponding source code. We evaluate AutoCrashFL against real-world crashes of SAP HANA, an industrial software project consisting of more than 35 million lines of code. Experiments reveal that AutoCrashFL is more effective in localization, as it identified 30% crashes at the top, compared to 17% achieved by the baseline. Through thorough analysis, we find that AutoCrashFL has attractive practical properties: it is relatively more effective for complex bugs, and it can indicate confidence in its results. Overall, these results show the practicality of LLM agent deployment on an industrial scale.

Lukas Schmidbauer, Carlos A. Riofrío, Florian Heinrich et al.

Real-world optimization problems must undergo a series of transformations before becoming solvable on current quantum hardware. Even for a fixed problem, the number of possible transformation paths -- from industry-relevant formulations through binary constrained linear programs (BILPs), to quadratic unconstrained binary optimization (QUBO), and finally to a hardware-executable representation -- is remarkably large. Each step introduces free parameters, such as Lagrange multipliers, encoding strategies, slack variables, rounding schemes or algorithmic choices -- making brute-force exploration of all paths intractable. In this work, we benchmark a representative subset of these transformation paths using a real-world industrial production planning problem with industry data: the optimization of work allocation in a press shop producing vehicle parts. We focus on QUBO reformulations and algorithmic parameters for both quantum annealing (QA) and the Linear Ramp Quantum Approximate Optimization Algorithm (LR-QAOA). Our goal is to identify a reduced set of effective configurations applicable to similar industrial settings. Our results show that QA on D-Wave hardware consistently produces near-optimal solutions, whereas LR-QAOA on IBM quantum devices struggles to reach comparable performance. Hence, the choice of hardware and solver strategy significantly impacts performance. The problem formulation and especially the penalization strategy determine the solution quality. Most importantly, mathematically-defined penalization strategies are equally successful as hand-picked penalty factors, paving the way for automated QUBO formulation. Moreover, we observe a strong correlation between simulated and quantum annealing performance metrics, offering a scalable proxy for predicting QA behavior on larger problem instances.

Senthil Kumar Jagatheesaperumal, Mohamed Rahouti, Ali Alfatemi et al.

Federated Learning (FL) represents a paradigm shift in machine learning, allowing collaborative model training while keeping data localized. This approach is particularly pertinent in the Industrial Internet of Things (IIoT) context, where data privacy, security, and efficient utilization of distributed resources are paramount. The essence of FL in IIoT lies in its ability to learn from diverse, distributed data sources without requiring central data storage, thus enhancing privacy and reducing communication overheads. However, despite its potential, several challenges impede the widespread adoption of FL in IIoT, notably in ensuring interpretability and robustness. This article focuses on enabling trustworthy FL in IIoT by bridging the gap between interpretability and robustness, which is crucial for enhancing trust, improving decision-making, and ensuring compliance with regulations. Moreover, the design strategies summarized in this article ensure that FL systems in IIoT are transparent and reliable, vital in industrial settings where decisions have significant safety and economic impacts. The case studies in the IIoT environment driven by trustworthy FL models are provided, wherein the practical insights of trustworthy communications between IIoT systems and their end users are highlighted.

Yan Chen, Cheng Liu

Remaining useful life (RUL) prediction is crucial for maintaining modern industrial systems, where equipment reliability and operational safety are paramount. Traditional methods, based on small-scale deep learning or physical/statistical models, often struggle with complex, multidimensional sensor data and varying operating conditions, limiting their generalization capabilities. To address these challenges, this paper introduces an innovative regression framework utilizing large language models (LLMs) for RUL prediction. By leveraging the modeling power of LLMs pre-trained on corpus data, the proposed model can effectively capture complex temporal dependencies and improve prediction accuracy. Extensive experiments on the Turbofan engine's RUL prediction task show that the proposed model surpasses state-of-the-art (SOTA) methods on the challenging FD002 and FD004 subsets and achieves near-SOTA results on the other subsets. Notably, different from previous research, our framework uses the same sliding window length and all sensor signals for all subsets, demonstrating strong consistency and generalization. Moreover, transfer learning experiments reveal that with minimal target domain data for fine-tuning, the model outperforms SOTA methods trained on full target domain data. This research highlights the significant potential of LLMs in industrial signal processing and RUL prediction, offering a forward-looking solution for health management in future intelligent industrial systems.

Stepan Patsenko , Yurii Gannenko

У статті, на основі функціонування логістичної системи Збройних сил України, визначено основні проблемні питання, що пов’язані з постачанням матеріальними засобами військ (сил) Збройних сил України, запропоновано заходи стосовно впровадження сучасних інформаційних технологій в логістичну систему Збройних сил України з метою поліпшення ефективності та оптимізації цього процесу. У процесі дослідження застосовано метод системного аналізу. Зазначений методологічний підхід дозволяє прогнозувати постачання матеріальними засобами, створювати інтегровані системи управління та контролю їх руху, розробляти системи логістичного обслуговування, оптимізувати запаси з використанням інформаційних технологій. Останнім часом, з моменту отримання міжнародної технічної допомоги від країн-партнерів, значна увага надається аспектам постачання матеріальними засобами військам (силам) Збройних сил України. Так, з моменту повномасштабного вторгнення військ російської федерації в Україну, Збройні сили України, за умови задовільного постачання під час бойових дій, продемонстрували власну спроможність виконувати бойові завдання згідно їхнього прямого призначення. З метою підвищення ефективності функціонування системи постачання матеріальними засобами Збройних сил України проаналізовано досвід провідних країн світу. Країни, які входять до НАТО використовують різні автоматизовані системи управління логістичною системою. Зокрема, під час проведення міжнародних навчань і тренувань, вони застосовують спеціалізоване програмне забезпечення LOGFAS. Також у статті сформульовані напрями подальших досліджень щодо удосконалення системи постачання матеріальними засобами військ (сил) Збройних сил України з використанням інформаційних технологій. Стаття має важливе прикладне значення, оскільки запропоновані заходи дадуть змогу підвищити ефективність постачання матеріальними засобами військ (сил) Збройних сил України, скоротити час на одержання та всебічне оцінювання відомостей про військове майно на всіх етапах його руху, а також збільшити ефективність підтримки військ (сил) і покращити взаємодію з аналогічними системами країн-партнерів НАТО.

Ni Luh Gede Aris Maytadewi Negara, I.A. Pascha Paramurthi, Ni Ketut Putri Purnama Dewi

Introduction: TBS textile factory is one of several textile factories where the process of fabrics dyeing takes place. In the process, workers lift and transport cloth loads manually, and thus work routines make their body bend. TBS textile factory ignored the health and safety aspects of work procedures which could cause worker fatigue. Safe work behaviour may prevent occupational sickness if the company applies appropriate occupational safety and health procedures. The purpose of this study was to determine the reduction of worker fatigue in the dyeing process of woven fabrics by applying occupational safety and health procedures. Methods: This study used treatment by subject design, where all samples were subjected to control and treatment, in different time periods. In this design, the interval between the time periods required washing out and adaptation, to eliminate the effects of previous work. The research population were workers in charge of dyeing section at TBS textile factory located in Gianyar regency. This study was conducted in July 2021 by involving 20 samples selected through purposive sampling technique. Data were collected from occupational safety and health procedures (how workers lifted and transported loads), legal limitations, and worker postures. Data analysis was carried out using t-independent test. Results: There was a decrease in scores of worker fatigue. The two different tests showed the scores after the study were significantly different (p < 0.05). Conclusion: Occupational safety and health procedures can reduce fatigue among workers in charge of fabrics dyeing by 40.77%.

Mustafa Yurdakul, Sakir Tasdemir

Detecting machine malfunctions at an early stage is crucial for reducing interruptions in operational processes within industrial settings. Recently, the deep learning approach has started to be preferred for the detection of failures in machines. Deep learning provides an effective solution in fault detection processes thanks to automatic feature extraction. In this study, a deep learning-based system was designed to analyze the sound signals produced by industrial machines. Acoustic sound signals were converted into Mel spectrograms. For the purpose of classifying spectrogram images, the DenseNet-169 model, a deep learning architecture recognized for its effectiveness in image classification tasks, was used. The model was trained using the transfer learning method on the MIMII dataset including sounds from four types of industrial machines. The results showed that the proposed method reached an accuracy rate varying between 97.17% and 99.87% at different Sound Noise Rate levels.

Christoph Nölle, Petri Kannisto

In the pursue for sustainability in process industry, digital twins necessitate the communication and storage of timeseries data about Industrial Internet of Things (IIoT). Regarding timeseries, this paper first presents a set of requirements specific to process industries. Then, it surveys how existing IIoT technologies meet the requirements. The technologies include the API specifications Asset Administration Shell (AAS), Digital Twin Definition Language (DTDL), NGSI-LD and Open Platform Communications Unified Architecture (OPC UA) as well as six commercial platforms. All the technologies leave significant gaps regarding the requirements, which means that tailor-made extensions are necessary.

Д. С. Гальченко

Kojiro Kawano, Saori Haga, Kenji Endo et al.

Objective: To evaluate the employment outcomes and changes in cognitive and social functioning of people with mental disorders using an employment support program in collaboration with psychiatric day care and the public employment service. Methods: This was a prospective, open-label, single-arm preliminary study. The employment support program was conducted 6 hours at a time, five times per week for 3 months. Participants’ employment rates within 6 months after the program ended and competitive employment in supported employment service 1 year later were calculated. The brief assessment of cognition in schizophrenia (BACS), Global Assessment of Functioning (GAF), and Life Assessment Scale for the Mentally Ill (LASMI) were measured before and after the program. Results: Forty-one (74.5%) of the 55 participants worked within 6 months of completing the program. Of the 30 employees who had been working for 1 year, 23 (76.7%) had settled in the workplace, with an average of over 80 monthly working hours and more than ＄660 monthly income. BACS Composite score (p&lt;0.01, r=0.68), GAF (p&lt;0.01, r=0.47), LASMI daily living (p&lt;0.01, r=0.44), interpersonal relations (p&lt;0.01, r=0.55), Work (p&lt;0.01, r=0.81), endurance and stability (p&lt;0.01, r=0.65), and self-recognition (p&lt;0.01, r=0.78) improved significantly after the program. Conclusion: Our study suggests that a high employment rate can be obtained by employment support in which psychiatric day care and the public employment service cooperate.

Yanbing Chen, Seamus Kelly, Conor Buggy

Introduction: Considerable media attention has recently focused on an increased number of professional athletes that experience forced retirement due to severe injuries. Despite the highly completive, physical nature and tolerance of risk in contact sports, no Occupational Safety and Health (OSH) awareness-related measurement instrument exists in professional sports. As part of a wider project, this study aimed to develop a survey instrument to evaluate risk and safety awareness in sports, taking elite rugby (union) as an example. Methods: Based on the identified conceptual framework incorporating theories from the OSH discipline, the survey has been updated for three rounds according to the feedback from a multidisciplinary team of experts before the pilot test. The pilot test data (n=46, response rate 76.7%) were imported to SPSS for analysis and validation. The survey's key themes included health outlook, tackle behavior, awareness of risk acceptance, reasons for risk-taking, and safety consideration for other players. Results: Overall, the survey has a high internal consistency (Cronbach's α= 0.742). Some sections of the survey require a further factor analysis, such as awareness of risk acceptance during the competition (Kaiser-Meyer-Olkin Measure of Sampling Adequacy - KMO <0.767, p<0.001) and reasons for risk-taking (KMO<0.604, p=0.003). Some sections require a larger sample size for further validation, such as safety consideration for other players (KMO<0.481, p<0.001). Conclusion: This is the first survey that evaluates players' safety and risk awareness in rugby drawing upon OSH concepts. Such a survey has the potential to improve athletes' health and wellbeing by customized educational intervention, which could point the way forward for its application in a wider range of sport settings internationally.

M. S. Egorov, R. V. Egorova, G. G. Tsordanidi

Introduction. Recently, sintered materials and products made of them have been increasingly used in powder metallurgy. In this regard, the issue of obtaining sintered products with high performance properties is acute. To achieve such properties, the materials are subjected to heat treatment. This procedure significantly affects their structure and mechanical properties. In production, sintered materials are most often subjected to subsequent hardening and tempering, as a result of which their equilibrium structure is established, grain growth stops, and strength characteristics improve.The article discusses the problems that arise in the formation of the qualitative structure of dispersed-hardened alloys as a result of their heat treatment.Problem Statement. The objective of this work is to study the phase changes in the process of cooling of powder steels and alloys in order to determine the modes of their heat treatment in order to form optimal conditions for the martensitic transformation of austenite.Theoretical Part. Phase transformations in powder steels occur in the temperature range at which their structures are rearranged, and as a result, the properties of the material change. The main factors affecting the phase transformations are the chemical composition of the alloy, the structure imperfection and the size of the grains. Changes in the structure and properties of alloys are considered in comparison with compact materials. Heat treatment significantly affects the phase and structural characteristics of powder materials, which are related to the mechanical characteristics of the alloys themselves.Conclusions. The conducted studies have shown that with an increase in the heterogeneity of the solid solution of steels, the temperature of the beginning of the martensitic transformation increased. A decrease in the temperature of the martensitic transformation with an increase in the degree of homogeneity of the solid solution occurs due to its enrichment with carbon and other alloying elements (chromium, molybdenum). With an increase in the percentage of carbon, an increase in the porosity of samples, the starting point of martensitic transformation also decreases. The temperature of the beginning of the martensitic transformation is not affected by carbides that are with austenite. These conclusions will help us to evaluate the mechanical properties of materials, as well as to develop recommendations for the practical application of heat treatment in the manufacture of products of complex shape.

N. V. Matyusheva, V. M. Khudyakova

Introduction. Vegetable production is one of the branches of plant cultivation that is distinguished by the specifics of conducting technological processes, characterized by the structural variety of cultivation facilities and special working conditions. Injuries of employees are the serious problem in the workplace now. The body of a worker is exposed to a complex of unfavorable production factors: mineral fertilizers, pesticides and products of their metabolism: heating microclimate, high humidity, significant physical exertion. If agrotechnical techniques are followed, they cannot be a source of deterioration of health. Violation of sanitary and hygienic regulations and technological schemes for growing crops increases the risk of health problems and affects the ability to work.Problem Statement. The task for the study is to develop a simplified design to lower vegetables into storage, improve working conditions and safety of workers. Theoretical Part. Occupational safety improvement in agriculture is necessary, first of all, from the point of the preservation and purpose of the system as a mechanism for protecting the interests of workers, guaranteeing the preservation of their life, health, working capacity in the process of professional activity, as well as for the purpose of agricultural production efficiency. There is an urgent problem of safety when laying vegetables in containers. The main type of injury to workers is occurred during work for eliminating technical and technological failures. Conclusions. As a result of the research, market analysis and evaluation of the competitiveness of the development under consideration, the main distinguishing features of the proposed device from the existing ones are determined. This design can be recommended for further integration into the existing enterprise system, as well as for use in any agricultural enterprises.

Sebastian Ulewicz, Birgit Vogel-Heuser

When changes are performed on an automated production system (aPS), new faults can be accidentally introduced in the system, which are called regressions. A common method for finding these faults is regression testing. In most cases, this regression testing process is performed under high time pressure and on-site in a very uncomfortable environment. Until now, there is no automated support for finding and prioritizing system test cases regarding the fully integrated aPS that are suitable for finding regressions. Thus, the testing technician has to rely on personal intuition and experience, possibly choosing an inappropriate order of test cases, finding regressions at a very late stage of the test run. Using a suitable prioritization, this iterative process of finding and fixing regressions can be streamlined and a lot of time can be saved by executing test cases likely to identify new regressions earlier. Thus, an approach is presented in this paper that uses previously acquired runtime data from past test executions and performs a change identification and impact analysis to prioritize test cases that have a high probability to unveil regressions caused by side effects of a system change. The approach was developed in cooperation with reputable industrial partners active in the field of aPS engineering, ensuring a development in line with industrial requirements. An industrial case study and an expert evaluation were performed, showing promising results.