Search in Publications

Found 6278 publications

A hybrid physics-informed neural and explainable AI approach for scalable and interpretable AQI predictions

Dragan Pamucar Rajesh Kumar Dhanaraj Malathy Sathyamoorthy Firoz Khan C. Sai Varun Balamurugan Balusamy Sunaina Sridhar Rajesh Kumar Dhanaraj Sai Varun Chandrashekar

Publication Name: Methodsx

Publication Date: 2025-12-01

Volume: 15

Issue: Unknown

Page Range: Unknown

Description:

Air Pollution is a critical environmental issue affecting public health, climate, and ecosystems. However, accurately predicting and classifying Air Quality Index (AQI) levels across different regions remains a challenging task due to the complex nature of air pollution patterns. Conventional and ensemble ML and DL models often fail to capture the physical laws goverming the air pollution, which leads to inaccurate predictions. This study addresses these issues by introducing an approach that employs Physics-Informed Neural Networks (PINN) with Explainable AI (XAI) techniques for AQI classification (AirSense-X). The proposed approach utilizes PINN for regression, along with mapping for classification and XAI for interpretation. PINN ensures that the model learns from physical laws governing air quality rather than relying solely on data. The dataset utilized in this study is a publicly available dataset containing the AQI data at daily levels from various stations across multiple cities in India. The proposed AirSense-X approach achieves an accuracy of 98 %, with 97 % precision, 95 % recall, and an F1 score of 0.96, ensuring reliability. Similarly, the confusion matrix for the proposed approach indicated that the model correctly classified 21,306 and misclassified 268 instances. The key focuses of this study include: • Introducing a novel approach, AirSense-X, which employs PINN for accurate AQI prediction and XAI for enhanced interpretability. Additionally, the study also involves comparative analysis with conventional and ensemble ML and DL models. • Employing structure mapping technique for classification based on the predicted AQI values. • Integrating physical laws governing air pollution using a PINN model enhances prediction accuracy and ensures that the model learns beyond relying on data-driven insights.

Open Access: Yes

DOI: 10.1016/j.mex.2025.103597

Bridging the divide: Addressing social tensions between internally displaced persons and host communities during wartime in Ukraine

Yuriy Bilan Halyna Mishchuk Natalia Samoliuk Olena Oliinyk

Publication Name: Problems and Perspectives in Management

Publication Date: 2025-01-01

Volume: 23

Issue: 3

Page Range: 645-657

Description:

Forced migration of Ukraine’s population, caused by the war initiated by the russian federation, is a subject of national governance in demographic processes. In a country at war – rapidly losing human potential due to casualties among military and civil populations, as well as forced relocations – the social relations between internally displaced persons (IDPs) and host communities are of critical importance. The aim of this paper is to assess the perceptions of IDPs in host communities and to identify factors contributing to potential social tension. The research is based on a nationally representative sociological survey conducted in June–July 2024 in Ukraine, involving 514 IDPs and 850 residents of host communities. The findings reveal that social tension is generally low, with most ratings no higher than 3 out of 5. Notably, one-third of host community residents and two-thirds of IDPs did not observe any tension in social interactions at all. IDPs tended to be more optimistic in their evaluations compared to host community members: their perception was significantly lower, with only 7.3% reporting high levels of strain (4-5 out of 5). In contrast, the host population’s evaluations were more critical, particularly among young people and residents of regional centers, who expressed the most negative views. Key factors contributing to tension included negative changes in the housing market (44.8% of host community respondents), increased pressure on healthcare institutions (29.3%), and greater demand for administrative services (26.2%). The results highlighted the need for regular monitoring, which should complement traditional social management practices.

Open Access: Yes

DOI: 10.21511/ppm.23(3).2025.46

Deep Learning-Based Approach for Autonomous Vehicle Localization: Application and Experimental Analysis

Krisztian Enisz Ernö Horváth Istvan Szalay Norbert Marko

Publication Name: Machines

Publication Date: 2023-12-01

Volume: 11

Issue: 12

Page Range: Unknown

Description:

In a vehicle, wheel speed sensors and inertial measurement units (IMUs) are present onboard, and their raw data can be used for localization estimation. Both wheel sensors and IMUs encounter challenges such as bias and measurement noise, which accumulate as errors over time. Even a slight inaccuracy or minor error can render the localization system unreliable and unusable in a matter of seconds. Traditional algorithms, such as the extended Kalman filter (EKF), have been applied for a long time in non-linear systems. These systems have white noise in both the system and in the estimation model. These approaches require deep knowledge of the non-linear noise characteristics of the sensors. On the other hand, as a subset of artificial intelligence (AI), neural network-based (NN) algorithms do not necessarily have these strict requirements. The current paper proposes an AI-based long short-term memory (LSTM) localization approach and evaluates its performance against the ground truth.

Open Access: Yes

DOI: 10.3390/machines11121079

Investigation of the long-term stability of various tinctures belonging to the lamiaceae family by HPLC and spectrophotometry method

E. Lakatos V. Kapcsándi Székelyhidi Rita Beatrix Sik Zsolt Ajtony

Publication Name: Chemical Papers

Publication Date: 2021-11-01

Volume: 75

Issue: 11

Page Range: 5781-5791

Description:

The aim of the current study was to analyze the stability of rosmarinic acid in ethanolic tinctures of lemon balm (Melissa officinalis L.), oregano (Origanum vulgare L.), peppermint (Mentha x piperita), rosemary (Rosmarinus officinalis L.), sage (Salvia officinalis L.), and thyme (Thymus vulgaris L.). High-performance liquid chromatography with diode-array detection (HPLC–DAD) was employed to monitor the concentration of the marker compound over a six month period. Furthermore, the tinctures were also evaluated for caffeic acid, total phenolic content, and 2,2-diphenyl-1-picrylhydrazyl (DPPH) scavenging activity. We observed that the concentration of rosmarinic acid in tincture stored in closed amber glasses at ambient temperature decreased significantly during 6-month storage. Furthermore, our study squarely confirms the fact that a part of rosmarinic acid is converted to caffeic acid. The tested tinctures can be listed in the following order according to the greatest stability of the marker compound: rosemary > peppermint > oregano > lemon balm > thyme > sage. The results of the study indicated a linear relationship between DPPH values and total phenolic (R2 = 0.92) or rosmarinic acid (R2 = 0.85) contents.

Open Access: Yes

DOI: 10.1007/s11696-021-01755-z

Experimental Analysis on the Hysteresis Phenomenon in the Range of Subsynchronous Frequency as a Function of Oil Temperature with Regard to Turbochargers

Cs Tóth-Nagy Gusztáv Fekete Márk Pesthy Máté Boros

Publication Name: Lubricants

Publication Date: 2025-02-01

Volume: 13

Issue: 2

Page Range: Unknown

Description:

This study presents an experimental analysis of a turbocharger with semi-floating ring bearings, focusing on hysteresis in subsynchronous vibrations. Four automotive oils (SAE 0W-20, SAE 0W-30, SAE 5W-30, SAE 5W-40) were tested across six oil inlet temperatures from 20 °C to 120 °C during ramp-up and ramp-down cycles to examine the effects of lubricant viscosity and temperature on rotor dynamics. Hysteresis and bifurcation points were observed at distinct rotational speeds in both directions, with subsynchronous components providing insights into rotor–lubrication interactions. This study applies the concept of hysteresis loop width for turbocharger rotors, highlighting its nonlinear dependence on oil temperature, an unexpected and unexplained phenomenon. Additionally, the results suggest that vibration sensors could provide real-time feedback on oil supply conditions, offering potential enhancements for turbochargers and other rotating machinery.

Open Access: Yes

DOI: 10.3390/lubricants13020060

A rapid and efficient DNA isolation method for qPCR-based detection of pathogenic and spoilage bacteria in milk

Balázs Ásványi K. Szenthe István Gyurján Barbara Bánkuti Bettina Pancza Zsófia Sipos-Kozma Miklós Szathmáry Zoltán Tudós F. Bánáti Susan Szathmary László Stipkovits László Varga

Publication Name: Food Control

Publication Date: 2021-12-01

Volume: 130

Issue: Unknown

Page Range: Unknown

Description:

The objective of this study was to find an efficient, rapid, simple, and cost-effective method of pretreating raw milk samples to produce PCR-ready DNA for subsequent microbial detection using the strains of eight bacterial species. A total of 17 in-house protocols and three commercial kits were evaluated in three steps from scientific, practical, and economic perspectives. The results showed that an in-house procedure involving Triton X-100-based pretreatment and an inhibitor removal resin was superior to all other methods tested in terms of DNA yield, sensitivity, ease of sample handling, time efficiency, and cost per sample. Overall, this simplified preanalytical protocol was shown to have a great potential for use in rapid detection of dairy-related bacterial species, thereby enabling early intervention in the food chain and thus reducing the risk of negative economic and health outcomes.

Open Access: Yes

DOI: 10.1016/j.foodcont.2021.108236

A Hands-On Demonstration of Control Performance Optimization Using Tensor Product Model Transformation and Convex Hull Manipulation

Peter Galambos Peter Varlaki Jozsef Kuti Péter Baranyi

Publication Name: Proceedings 2015 IEEE International Conference on Systems Man and Cybernetics Smc 2015

Publication Date: 2016-01-12

Volume: Unknown

Issue: Unknown

Page Range: 2609-2614

Description:

In polytopic model based controller synthesis, the vertices of the model determine the achievable performance. This paper demonstrates a complete and tractable design process exposing the polytopic qLPV model generation and a polytopeshaping technique through the example of the TORA (Translational Oscillator with a Rotational Actuator) system. The demonstrated apparatus allows for systematically improving the control performance through the manipulation of the polytopic structure based on the MVSA (Minimal Volume Simplex Analysis) algorithm. The proposed approach fits to the framework of TP Model Transformation.

Open Access: Yes

DOI: 10.1109/SMC.2015.456

Strategizing for Sustainability: Examining the Dynamic Interplay of the Circular Economy, Green Technology Innovation, and Green Performance

Mohammad Imtiaz Hossain Mohammad Fakhrul Islam Md Faisal-E-Alam Mohammad Imran Hossain Md Rashed Md Naeemur Rahman

Publication Name: Global Journal of Flexible Systems Management

Publication Date: 2025-12-01

Volume: 26

Issue: 4

Page Range: 935-961

Description:

Environmental challenges critically affect manufacturing firms which face numerous concerns regarding their sustainable operations. These operations aim to operationalize the dimensions of circular economy capabilities (CEC) and green technology innovation (GTI) to strengthen competitiveness in fragile environments. This research validates a holistic understanding of green performance by integrating theories and dimensions to identify effects that predict sustainable green performance. Drawing from the green dynamic capability view (GDCV), which is a contextual extension of the DCV and flexible systems management (FSM) paradigm, this study investigates how CEC and GTI predict green performance (GP). Survey data of 301 senior professionals from manufacturing firms acquired from a developing country, such as Bangladesh, were used. To assess the survey data, the study used a multimethodological approach using Necessary Condition Analysis (NCA) and fuzzy-set Qualitative Comparative Analysis (fsQCA) to investigate the suggested tie in the midst of the CEC and GTI on the GP. The findings reveal that all the antecedents of the circular economy are necessary conditions except absorptive capacity to predict green performance, as reported in the NCA. The fsQCA results show that combinations of CEC and GTI are sufficient conditions to predict high green performance. This research uses a unique combination of CEC and GTI to predict high GP via the supplementary method of fsQCA. Therefore, the findings should also motivate professionals of manufacturing firms to focus even more on the necessity effects of a single condition to predict GP and the asymmetric effects of combinations of CEC and GTI to produce multiple configurations to predict high green performance.

Open Access: Yes

DOI: 10.1007/s40171-025-00469-5

RFId applications in the supply chain

Tamás Hartványi József Marek

Publication Name: 2007 1st Annual Rfid Eurasia

Publication Date: 2007-12-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

It is a fact that Radio Frequency Identification technology (RFId) can benefit enterprises and contribute to their integration to supply chains. Several issues emerge concerning technology and economy of introducing and applying the system, especially in small and medium sized businesses. In 2005 Department of Logistics and Forwarding of Széchenyi István University joined the program INTERREG IIIC "REGINSrfld" initiated by the Community of the European Union. The purpose of the program is to examine possibilities of introducing of RFId in small and medium-sized businesses. We completed the project in cooperation with German, Austrian and Italian partners in June 2006.

Open Access: Yes

DOI: 10.1109/RFIDEURASIA.2007.4368132