Search in Publications

Found 6278 publications

Weed detection in agricultural fields using machine vision

Bálint Ambrus Gergely Teschner László Moldvai A. Nyéki

Publication Name: Bio Web of Conferences

Publication Date: 2024-08-23

Volume: 125

Issue: Unknown

Page Range: Unknown

Description:

Weeds have the potential to cause significant damage to agricultural fields, so the development of weed detection and automatic weed control in these areas is very important. Weed detection based on RGB images allows more efficient management of crop fields, reducing production costs and increasing yields. Conventional weed control methods can often be time-consuming and costly. It can also cause environmental damage through overuse of chemicals. Automated weed detection and control technologies enable precision agriculture, where weeds are accurately identified and targeted, minimizing chemical use and environmental impact. Overall, weed detection and automated weed control represent a significant step forward in agriculture, helping farmers to reduce production costs, increase crop safety, and develop more sustainable agricultural practices. Thanks to technological advances, we can expect more efficient and environmentally friendly solutions for weed control in the future. Developing weed detection and automated control technologies is crucial for enhancing agricultural efficiency. Employing RGB images for weed identification not only lowers production costs but also mitigates environmental damage caused by excessive chemical use. This study explores automated weed detection systems, emphasizing their role in precision agriculture, which ensures minimal chemical use while maximizing crop safety and sustainability.

Open Access: Yes

DOI: 10.1051/bioconf/202412501004

Scenario-driven decision models for rare element waste management by integrating koch snowflake fuzzy sets and euclidean expert weighting

Dragan Pamucar Hasan Dincer Serhat Yuksel Serkan Eti Merve Acar Vladimir Simic

Publication Name: Sustainable Futures

Publication Date: 2025-12-01

Volume: 10

Issue: Unknown

Page Range: Unknown

Description:

The most critical factors must be determined to effectively manage environmental wastes generated during the extraction of rare elements. Otherwise, businesses may not be able to effectively manage their limited financial and human resources. This situation negatively affects the financial performance of the projects. The limited number of existing studies in the literature causes environmental risks to be insufficiently managed and recycling processes to be unoptimized. This study aims to determine priority strategies to increase the effectiveness of rare element waste management processes. Comprehensive and original decision-making models are created under three different scenarios. Koch Snowflake fuzzy sets, Euclidean based expert weighting and cognitive information modelling and analysis system (CIMAS) approaches are integrated in this model. The main contribution of this study is that a new type of fuzzy numbers called Koch Snowflake fuzzy sets is developed by considering the concept of fractal numbers. Fractal geometry is a powerful tool for modelling complex and dynamic systems. Hence, these new sets provide more flexible and more detailed uncertainty modelling. Moreover, considering different scenarios dynamic strategies can be developed that can adapt to changing conditions, such as pandemics or trade wars. The findings denote that technological developments are determined as the most critical factor under normal conditions. In the scenario where trade wars occur, it is revealed that political and regulatory measures should be addressed as a priority. In the event of a new epidemic disease such as COVID-19, it is concluded that more importance should be given to long-term storage strategies.

Open Access: Yes

DOI: 10.1016/j.sftr.2025.101490

Evaluation of Various Deep Learning Algorithms for Landslide and Sinkhole Detection from UAV Imagery in a Semi-arid Environment

Saied Homayouni Mohsen Hosseinalizadeh Hamid Reza Pourghasemi Omid Ghorbanzadeh Narges Kariminejad Hejar Shahabi Vahid Shafaie

Publication Name: Earth Systems and Environment

Publication Date: 2024-12-01

Volume: 8

Issue: 4

Page Range: 1387-1398

Description:

Sinkholes and landslides occur due to soil collapse in different slope types, often triggered by heavy rainfall, presenting challenges in the semi-arid Golestan province, Iran. This study primarily focuses on the detection of these phenomena. Recent advancements in unmanned aerial vehicle (UAV) image acquisition and the incorporation of deep learning (DL) algorithms have enabled the creation of semi-automated methods for highly detailed soil landform detection across large areas. In this study, we explored the efficacy of six state-of-the-art deep learning segmentation algorithms—DeepLab-v3+, Link-Net, MA-Net, PSP-Net, ResU-Net, and SQ-Net—applied to UAV-derived datasets for mapping landslides and sinkholes. Our most promising outcomes demonstrated the successful mapping of landslides with an F1-Score of 0.95% and sinkholes with an F1-Score of 89% in a challenging environment. ResUNet exhibited an outstanding Precision of 0.97 and Recall of 0.92, culminating in the highest F1-Score of 0.95, indicating the best landslide detection model. MA-Net and SQ-Net resulted in the highest F1-Score for sinkhole detection. Our study underscores the significant impact of DL segmentation algorithm selection on the accuracy of landslide and sinkhole detection tasks. By leveraging DL segmentation algorithms, the accuracy of both landslide and sinkhole detection tasks can be significantly improved, promoting better hazard management and enhancing the safety of the affected areas.

Open Access: Yes

DOI: 10.1007/s41748-024-00419-8

Improvement of soil fertility and enzymatic activity by wastewater sludge compost and arbuscular mycorrhizal fungi in giant reed's rhizosphere

Anna Füzy Imre Cseresnyés Tünde Takács Ambrus Rév Katica Kocsis Péter Juhász István Parádi

Publication Name: Biologia Futura

Publication Date: 2025-12-01

Volume: 76

Issue: 4

Page Range: 559-575

Description:

The effect of low-dose, commercially available wastewater sludge compost (WSC; 15 t ha−1) treatment was examined with or without arbuscular mycorrhizal fungal (AMF) inoculation on the nutritional status, heavy metal (HM) concentration and the rhizosphere activity of giant reed (Arundo donax L. var. BL clone (Blossom)) plants. Funneliformis mosseae (BEG12; AMF1), F. geosporum (BEG11; AMF2) or their combination (AMFmix) were applied as AMF treatments in a short-term pot experiment. The physiological and growth parameters of the host plants, the AMF root colonization and the microbiological enzyme activity of the mycorrhizosphere were examined. We assumed that the combined treatment (WSC + AMF) enhances the fertility of low-fertility acidic sandy soil. Neither the WSC treatment nor the AMF inoculations changed the extent of root colonization. Based on the results of root electrical capacitance and the phosphorous uptake, plant nutritional status was improved by WSC addition, without any negative impacts among the measured parameters. AMF treatments increased the enzyme activity in the soil and decreased the concentrations of the potentially toxic HMs (Cu, Mn, Pb, Zn) in roots, but that mitigation of Cu and Zn was compensated in shoots. According to the results of MicroResp™ measurements, the catabolic activity profile of the soil microbial community was changed in case of the AMF2 treatment. The efficient regulatory mechanism of giant reed might be able to adjust optimal/maximal colonization rate, and to select the preferential AMF partners, this supposed mechanism might be responsible for its invasiveness and tolerance to a wide range of environmental conditions.

Open Access: Yes

DOI: 10.1007/s42977-025-00286-y

Application of atomic spectroscopy for trace element analysis of fruit juices: a review

Pavithra Hemachandra Zsolt Ajtony László Bencs

Publication Name: Bio Web of Conferences

Publication Date: 2024-08-23

Volume: 125

Issue: Unknown

Page Range: Unknown

Description:

Trace elements are crucial for human nutrition, requiring their precise analysis in fruit juices to ensure product quality and assess contamination risks. Atomic spectroscopy techniques including inductively coupled plasma mass spectrometry (ICP-MS), inductively coupled plasma optical emission spectrometry (ICP-OES), graphite furnace atomic absorption spectrometry (GFAAS), flame atomic absorption spectrometry (FAAS), atomic fluorescence spectrometry (AFS), X-ray fluorescence spectrometry (XRF), and glow discharge optical emission spectrometry (GD-OES) are sensitive, selective and versatile tools for trace element analysis of various solid and solution samples. Matrix modifiers, sample introduction and sample preparation methods are pivotal for improving the accuracy and mitigating matrix interferences. Further advancements in instrumentation are essential. This review provides a comprehensive overview of these techniques, highlighting their principles, advantages, limitations and future research directions in fruit juice analysis. Its global applications, focusing on As, Cd, Co, and Pb, along with sample preparation methods, element concentrations, detection limits, and recovery values, have been explored.

Open Access: Yes

DOI: 10.1051/bioconf/202412502003

Spectral moment segmentation and spectrogram synthesis for simulation of road vehicle vibrations

László Róbert Hári

Publication Name: Mechanical Systems and Signal Processing

Publication Date: 2022-11-15

Volume: 180

Issue: Unknown

Page Range: Unknown

Description:

Vibration testing procedures relying solely on a Fourier profile can introduce only stationary random vibrations. It is in contrast with the non-stationary and non-Gaussian nature of the Road vehicle vibrations (RVV). The following procedure segments the first four spectral moments of the time–frequency domain of RVV, constructs probability density arrays per frequency bins, and perform simulations according to random segment lengths and -root mean squares, yielding more realistic representations of RVV. The distribution of time- and frequency domain moments and normalized spectral entropies are confronted. The Probability-based spectrogram synthesis (PBSS) offers a data-driven stochastic modelling framework for simulating non-stationary RVV.

Open Access: Yes

DOI: 10.1016/j.ymssp.2022.109408

Speed and position control of BLDC servo systems with low inertia

Claudiu Pozna Mircea Bogdan Rǎdac Claudia Adina Dragos Alexandra Iulia Stînean Radu Emil Precup Stefan Preitl

Publication Name: 2011 2nd International Conference on Cognitive Infocommunications Coginfocom 2011

Publication Date: 2011-09-22

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

The paper deals with applicative aspects concerning the control of speed and position of a BLDC servo system with low but Variable in a given range Moment of Inertia (VMI). Detailed models of various applications, some control solutions are discussed and developed and part of them tested on the basis of the specific features of the plants with VMI. The adopted control solutions PI(D) control (as reference solution) and fuzzy control with homogenous and non-homogenous dynamics are briefly presented and some approaches regarding the methods are highlighted. Due to the applicability of the methods in the field of mechatronics applications with VMI (speed and positioning control of rapid plants), the presented aspects are of permanent actuality, and they offer directions of future research. © 2011 Scientific Assoc Infocomm.

Open Access: Yes

DOI: DOI not available

On tensor-product model based representation of neural networks

András Rövid Peter Varlaki Lászlõ Szeidl

Publication Name: Ines 2011 15th International Conference on Intelligent Engineering Systems Proceedings

Publication Date: 2011-08-22

Volume: Unknown

Issue: Unknown

Page Range: 69-72

Description:

The approximation methods of mathematics are widely used in theory and practice for several problems. In the framework of the paper a novel tensor-product based approach for representation of neural networks (NNs) is proposed. The NNs in this case stand for local models based on which a more complex parameter varying model can numerically be reconstructed and reduced using the higher order singular value decomposition (HOSVD). The HOSVD as well as the tensor-product based representation of NNs will be discussed in detail. © 2011 IEEE.

Open Access: Yes

DOI: 10.1109/INES.2011.5954721

A partial ordering approach for functional diversity

Marco Moretti Lászlõ Szeidl Carlo Blasi Carlo Ricotta

Publication Name: Theoretical Population Biology

Publication Date: 2011-09-01

Volume: 80

Issue: 2

Page Range: 114-120

Description:

Functional diversity is generally regarded as the constituent of biological diversity that considers how the species functional traits affect ecosystem processes. Due to its ecological relevance, a number of indices of functional diversity have been proposed to date based on distinct objectives and motivations. Such proliferation of indices can be at least partially overcome by a more fundamental mathematical approach. In this paper we propose an intrinsic ordering approach for abundance-weighted measures of functional diversity that is similar to the Lorenz curves used by ecologists for ordering evenness measures. We then discuss the relevance of a number of functional diversity indices that have a behavior compatible with the proposed partial ordering. © 2011 Elsevier Inc.

Open Access: Yes

DOI: 10.1016/j.tpb.2011.03.007