Original Dataset Research Articles

Improving Minority Class Recall through a Novel Cluster-Based Oversampling Technique

In this study, we propose an approach to address the pressing issue of false negative errors by enhancing minority class recall within imbalanced data sets commonly encountered in machine learning applications. Through the utilization of a cluster-based oversampling technique in conjunction with an information entropy evaluation, our approach effectively targets areas of ambiguity inherent in the data set. An extensive evaluation across a diverse range of real-world data sets characterized by inter-cluster complexity demonstrates the superior performance of our method compared to that of existing oversampling techniques. Particularly noteworthy is its significant improvement within the Delinquency Telecom data set, where it achieves a remarkable increase of up to 30.54 percent in minority class recall compared to the original data set. This notable reduction in false negative errors underscores the importance of our methodology in accurately identifying and classifying instances from underrepresented classes, thereby enhancing model performance in imbalanced data scenarios.

Against Dictatorship, against Backsliding? Examining the Effect of Serbian Anti-Government Protests on the 2020 Electoral Boycott

The power of the Serbian Progressive Party (SNS) has been steadily growing ever since 2012. The party has successfully taken control of all levels of government in Serbia, and the country has suffered from gradual democratic backsliding as a result. In this article, we focus on two protest waves in Serbia between 2017 and 2019. Crucially, a number of opposition parties involved in the more recent protest wave boycotted the 2020 parliamentary election. This article analyzes the characteristics of the citizen-led response in local communities across Serbia and estimates its electoral impact using a difference-in-differences approach. The case of Serbia not only elucidates modes of citizen response and their impact in post-Communist Europe but also provides comparative insights for the potential for citizen-led resistance to mobilize against backsliding in other countries. The objectives of the article are twofold. First, the article uses an original data set of Serbian protest events between 2017 and 2019 to ascertain how the two protest waves were conducted, and how citizens respond to democratic backsliding. Second, using data on municipal-level turnout and SNS vote share in the 2020 parliamentary election, we examine the average electoral impact of protest and, related to that, we evaluate the success of opposition parties in mobilizing voters for the electoral boycott. The article investigates whether SNS-led democratic backsliding is resilient to sustained citizen-led mobilization or whether this bottom-up resistance challenges the notion that “stabilitocracies” such as Serbia are immune to fundamental political change.

Stability of Northern Eurasia Based on Satellite Geodesy Data

The geodynamics of Northern Eurasia has been analyzed based on repeated satellite positioning with GNSS stations throughout the Russian Federation territory from 2015 to the present. The study utilized two sources of data: observations from the stations of the Russian Fundamental Astro-Geodetic Network (FAGN) and stations of the International GNSS Service (IGS) with permanent satellite tracking. This data set allowed to estimate correctness of the block kinematics of the Eurasian plate in three tectonic plate motion models: NUVEL-1A, NNR-MORVEL-56, and ITRF2014. The analysis of the misfits between the observed and model velocities has shown that these misfits have a systematic component in the vicinity of the East European Platform which differs for each of three models. In addition to analyzing the block kinematics of the Eurasian plate, we also evaluated its internal stability. To do this, we calculated the areal deformations of Northern Eurasia using the finite element method. For this purpose, we added the observations processing results from the global data set of the Nevada Geodetic Laboratory to the processing results from two original data sets. Besides interplate boundary deformations which are consistent with existing ideas of the geodynamics of Northern Eurasia, the strain field analysis also revealed intraplate deformations distributed consistently with the configuration of the Northern Eurasia cratons.

Structural adjustment, economic performance, and electoral volatility in presidential elections in Latin America

AbstractDrawing upon the Latin American Presidential and Legislative Elections database and our own original data set, we assess the effects of structural adjustment and other economic factors on presidential electoral volatility in 24 Latin American countries in 1982–2016. The results of our study indicate that both structural adjustment and inflation have a positive association with Type B presidential electoral volatility (the volatility generated from changes in the vote shares of established parties). Economic growth appears to have only a weak negative association with overall presidential electoral volatility. Type A presidential electoral volatility (the volatility associated with the rise of new parties) is mostly determined by demographic factors and the electoral system for the presidency. As with legislative volatility in Latin America, Africa, and postcommunist Europe, explaining stable party presidential volatility appears more challenging than explaining party replacement presidential volatility. Overall, several of the findings about legislative volatility are echoed in this study, but presidential electoral volatility is notably higher than legislative volatility in Latin America.

True lateral imaging during lumbar medial branch radiofrequency neurotomy: Interobserver reliability

BackgroundTrue lateral imaging (TLI), obtained by superimposing bilateral lumbar spine structures and aligning superior endplate cortical bone, requires deliberate rotational adjustments of the laterally positioned fluoroscope in both the axial and longitudinal planes. True lateral segmental imaging is necessary to depict true and accurate radiofrequency (RF) cannula positioning relative to bony anatomy during lumbar medial branch radiofrequency neurotomy (LMBRFN). ObjectiveTo determine the interobserver reliability of TLI during LMBRFN. MethodsThis was a retrospective review of a prospectively generated collection of lateral fluoroscopic images to determine the interobserver reliability of TLI during LMBRFN. Lateral fluoroscopic images were prospectively collected from 34 consecutive L4-5 and L5-S1 LMBRFN procedures during routine clinical practice. Employing International Pain and Spine Intervention Society (IPSIS) LMBRFN and TLI techniques, an RF cannula was positioned parallel to the L3 and L4 medial branches and the L5 dorsal rami. During the normal course of TLI, untrue and final true lateral segmental images were obtained and saved. An original data set of 100 pairs of true and untrue lateral images was reviewed to verify true laterality using established criteria; disagreement was resolved by consensus or discarding ambiguous cases. To measure interobserver reliability (Cohen's Kappa), two blinded expert reviewers independently reviewed the image set, identifying the true lateral image and the plane requiring correction. ResultsThe observers agreed upon 98/98 true lateral RF-segment images (Kappa score 1.0 [1.00,1.00]). The observers agreed upon 86/98 maneuvers to correct the untrue RF-segment image. The Kappa score for determining the most appropriate corrective maneuver was 0.76 (0.63,0.89), showing substantial interobserver agreement. ConclusionsThe true lateral image of the targeted RF segment during LMBRFN was reliably determined with perfect interobserver agreement. Interobserver agreement was substantial regarding the maneuver to achieve TLI.

Status threat: The core of reactionary politics

AbstractIn recent years, reactionary movements have overtaken the politics of western democracies and developing countries alike. Using the United States is a case in point, we offer a theory of what motivates reactionary movements. While controlling for conventional individual‐level accounts of reactionary psychological dispositions, we offer a fresh explanation: status threat. We argue that status threat, a reaction to rapid sociocultural change on the part of dominant groups, pushes some members of these groups into joining and supporting reactionary movements and parties, respectively. We first outline the social psychology of the group (White, Christian, patriarchal, native born, heteronormative) that animates a movement (MAGA) that, in turn, has taken over a party (the GOP). We then test a wide range of hypotheses using two original data sets, finding robust evidence to support our claim: status threat is a major source of the increasing fractionalization of American society and politics, one that threatens American democracy.

Aukštų pareigūnų skyrimas pusiau prezidentiniame modelyje: Lietuvos atvejis*

Both academics who study presidential powers and political practitioners acknowledge that Lithuanian president enjoys the power to appoint high-ranking officials. This article investigates the determinants of success (or failure) of presidential decrees by which nominations of high-ranking public officials are submitted to Seimas. Presented theory and results are also discussed in a wider context of literature on semi-presidentialism: what does this power say about the role of presidents and the functioning of such regimes? Analysis employs an original data set, which consists of 337 decrees by presidents of Lithuania from 1993 to 2023 that were submitted to Seimas for consent regarding the appointment of respective public officials. The statistical analysis is complemented by information from semi-structured interviews with several high-ranking politicians. The study reveals several key points. First, high success rate of decrees (about 92.7 percent) is explained by the incentives of the constitutional algorithm and the informal practice of coordinating nominations between the president and the ruling majority before submitting them to Seimas. Second, quantitative analysis and qualitative interviews reveal that the success of decrees increases with the judicial appointments that are advised by a body of experts (Council of Judges) and decreases with appointments to heads of institutions. Third, some cases can also be explained by personal characteristics of nominees: age (result of quantitative analysis) or their self-presentation to Seimas (semi-structured interviews). Fourth, cohabitation – when the president and the parliamentary majority are of different political camps – only partially explains the success of decrees. Some unsuccessful decrees occur because of a short-term drop in the “temperature” of intra-executive relationship. However, this drop usually bounces back to cooperation phase – thus, the power to appoint high-ranking officials contradicts popular paradigm of literature on semi-presidentialism, namely that sees the relationship between president and government as competitive. The president himself together with the system of checks and balances around this power almost ideally embody the moderating power: important condition is that the moderator himself is also constitutionally “moderated”.

Prospective validation of a hospital triage predictive model to decrease undertriage: an EAST multicenter study

BackgroundTiered trauma team activation (TTA) allows systems to optimally allocate resources to an injured patient. Target undertriage and overtriage rates of <5% and <35% are difficult for centers to achieve,...

An In-Silico Approach to Identify Therapeutic Target and Markers Associated with Diabetic Nephropathy.

Renal disease in T2DM could arise independent of hyperglycemia, aka non diabetic kidney disease. Their prevalence ranges from 33%to72.5% among T2DM patients. Specific molecular signatures that distinguish Diabetic Nephropathy from NDKD (FSGS) in T2DM might provide new targets for CKD management. Five original GEO microarray DN and FSGS datasets were evaluated (GSE111154, GSE96804, GSE125779, GSE129973 and GSE121233). Each of the three groups (DN, FSGS, and Controls) had equal renal transcriptome data (n=32) included in the analysis to eliminate bias. The DEGs were identified using TAC4.0. Pathway analysis was performed on the discovered genes that aligned to official gene symbols using Reactome, followed by functional gene enrichment analysis using Funrich,Enrichr. STRING and Network analyst investigated PPI, followed by Webgestalt's pathway enrichment. Finally, using the Targetscan7.0 and DIANA tools, filtered differential microRNAs downregulated in DN were evaluated for target identification. Between the three groups, DN, FSGS, and Control, a total of 194 DEGs. with foldchange >2&<-2 and P-value0.01 were found in the renal transcriptome. In comparison to control, 45 genes were elevated particularly in DN, whereas 43 were upregulated specifically in FSGS. DN datasets were compared to FSGS in a separate analysis. FABP4, EBF1, ADIRF, and ART4 were shown to be among the substantially up-regulated genes unique to DN in both analyses. The transcriptional regulation of white adipocytes was discovered by a pathway analysis. The molecular markers revealed might be employed as specific targets in the aetiology of DN, as well as in T2DM patients' therapeutic care.

The rise of Indo-German collaborative research: 1990–2022

Purpose This study aims to highlight the growth and development of Indo-German collaborative research over the past three decades. Moreover, this study encompasses an in-depth examination of funding acknowledgements to gain valuable insights into the financial support that underpins these collaborative endeavours. Together with this paper, the authors provide an openly accessible data set of Indo-German research papers for further and reproducible research activities (the “Indo-German Literature Dataset”). Design/methodology/approach The data were retrieved from the Web of Science (WoS) database from the year 1990 till the 30th of November 2022. A total of 36,999 records were retrieved against the used query. Acknowledged entities were extracted using a named entity recognition (NER) model specifically trained for this task. Interrelations between the extracted entities and scientific domains, lengths of acknowledgement texts, number of authors and affiliations, number of citations and gender of the first author, as well as collaboration patterns between Indian and German funders were examined. Findings The study reveals a consistent and increasing growth in the publication trend over the years. The study brings to light that Physics, Chemistry, Materials Science, Astronomy and Astrophysics and Engineering prominently dominate the Indo-German collaborative research. The USA, followed by England and France, are the most active collaborators in Indian and German research. Largely, research was funded by major German and Indian funding agencies, international corporations and German and American universities. Associations between the first author’s gender and acknowledged entity were observed. Additionally, relations between entity, entity type and scientific domain were discovered. Practical implications The study paves the way for enhanced collaboration, optimized resource utilization and societal advantages by offering a profound comprehension of the intricacies inherent in research partnerships between India and Germany. Implementation of the insights gleaned from this study holds the promise of cultivating a more resilient and influential collaborative research ecosystem between the two nations. Originality/value The study highlights a deeper understanding of the composition of the Indo-German collaborative research landscape of the past 30 years and its significance in advancing scientific knowledge and fostering international partnerships. Furthermore, the authors provide an open version of the original WoS data set. The Indo-German Literature Data set consists of 22,844 papers from OpenAlex and is available for related studies like literature studies and scientometrics.

How UN peacekeeping missions enforce peace agreements

AbstractHow do UN peacekeeping missions enforce peace agreements, and what effect do higher rates of enforcement have on agreement implementation and conflict termination? Peace agreement enforcement forms a central component of peacekeeping effectiveness, yet missions are often mandated to enforce a minority of agreement provisions, and they vary across both time and space in the ways in which they do so. I identify the three dimensions along which enforcement operates—the proportion and type of provisions that missions are mandated to enforce, alongside their mandated level of involvement in their implementation—and theorize about their positive effects on agreement implementation and conflict termination. Analyzing the Peacekeeping Enforcement Dataset, an original data set of the enforcement patterns of all UN peacekeeping missions (1989–2015), I find that each dimension of enforcement has, at various time points, a distinct impact on agreement implementation and preventing conflict recidivism.

Impact of transfer learning compared to convolutional neural networks on fruit detection

Smart farming, also known as precision agriculture or digital farming, is an innovative approach to agriculture that utilizes advanced technologies and data-driven techniques to optimize various aspects of farming operations. One smart farming activity, fruit classification, has broad applications and impacts across agriculture, food production, health, research, and environmental conservation. Accurate and reliable fruit classification benefits various stakeholders, from farmers and food producers to consumers and conservationists. In this study, we conduct a comprehensive comparative analysis to assess the performance of a Convolutional Neural Network (CNN) model in conjunction with four transfer learning models: VGG16, ResNet50, MobileNet-V2, and EfficientNet-B0. Models are trained once on a benchmark dataset called Fruits360 and another time on a reduced version of it to study the effect of data size and image processing on fruit classification performance. The original dataset reported accuracy scores of 95%, 93%, 99.8%, 65%, and 92.6% for these models, respectively. While accuracy increased when trained on the reduced dataset for three of the employed models. This study provides valuable insights into the performance of various deep learning models and dataset versions, offering guidance on model selection and data preprocessing strategies for image classification tasks.

NExT-OOD: Overcoming Dual Multiple-Choice VQA Biases.

In recent years, multiple-choice Visual Question Answering (VQA) has become topical and achieved remarkable progress. However, most pioneer multiple-choice VQA models are heavily driven by statistical correlations in datasets, which cannot perform well on multimodal understanding and suffer from poor generalization. In this paper, we identify two kinds of spurious correlations, i.e., a Vision-Answer bias (VA bias) and a Question-Answer bias (QA bias). To systematically and scientifically study these biases, we construct a new video question answering (videoQA) benchmark NExT-OOD in OOD setting and propose a graph-based cross-sample method for bias reduction. Specifically, the NExT-OOD is designed to quantify models' generalizability and measure their reasoning ability comprehensively. It contains three sub-datasets including NExT-OOD-VA, NExT-OOD-QA, and NExT-OOD-VQA, which are designed for the VA bias, QA bias, and VA&QA bias, respectively. We evaluate several existing multiple-choice VQA models on our NExT-OOD, and illustrate that their performance degrades significantly compared with the results obtained on the original multiple-choice VQA dataset. Besides, to mitigate the VA bias and QA bias, we explicitly consider the cross-sample information and design a contrastive graph matching loss in our approach, which provides adequate debiasing guidance from the perspective of whole dataset, and encourages the model to focus on multimodal contents instead of spurious statistical regularities. Extensive experimental results illustrate that our method significantly outperforms other bias reduction strategies, demonstrating the effectiveness and generalizability of the proposed approach.

Efficient Corrections for Standardized Person-Fit Statistics.

Many popular person-fit statistics belong to the class of standardized person-fit statistics, T, and are assumed to have a standard normal null distribution. However, in practice, this assumption is incorrect since T is computed using (a) an estimated ability parameter and (b) a finite number of items. Snijders (Psychometrika 66(3):331-342, 2001) developed mean and variance corrections for T to account for the use of an estimated ability parameter. Bedrick (Psychometrika 62(2):191-199, 1997) and Molenaar and Hoijtink (Psychometrika 55(1):75-106, 1990) developed skewness corrections for T to account for the use of a finite number of items. In this paper, we combine these two lines of research and propose three new corrections for T that simultaneously account for the use of an estimated ability parameter and the use of a finite number of items. The new corrections are efficient in that they only require the analysis of the original data set and do not require the simulation or analysis of any additional data sets. We conducted a detailed simulation study and found that the new corrections are able to control the Type I error rate while also maintaining reasonable levels of power. A real data example is also included.

Switching Triple-Weight-SMOTE in Empirical Feature Space for Imbalanced and Incomplete Data

Most existing techniques to handle imbalanced data might be invalid in the presence of data missing since they are based on the assumption that the data is complete. To shorten such a gap, a novel synthetic minority oversampling technique (SMOTE), i.e., Non-negative latent factor analysis-incorporated and Switching triple-weight-SMOTE (NSS), is proposed. The main idea of NSS is 4-fold: 1) a Lagrange non-negative matrix factorization (LNMF) method is put forward to impute the missing values with a guaranteed non-negativity according to the original distribution owing to the consideration of the global feature information; 2) by mapping the complete data after imputation into an empirical feature space (EFS), a more separable dataset is achieved, which rigidly maintains the same geometrical structure as the original data while efficiently reducing the redundant features to enhance model generalization and operational efficiency; 3) after fulfilling the fuzzy <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$c$</tex-math> </inline-formula> -means (FCM) clustering, the inter-cluster distance, the capacity of each minority cluster and its sparsity are comprehensively taken into account to develop a triple-weight assignment strategy, which contributes to allocate the number of synthetic samples to each cluster appropriately; 4) a switching oversampling strategy is provided in response to the clusters with different distributions (i.e., either Gaussian or uniform distribution). Moreover, a posterior is used to check the correctness of the synthetic samples. Finally, experiments on a real dataset and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$12$</tex-math> </inline-formula> public datasets show that the proposed NSS outperforms other <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$11$</tex-math> </inline-formula> state-of-art methods. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Data classification is an important computer task, which has been successfully used in many domains, including but not limited to, the medical domain, finance domain, and manufacturing domain. However, there are two big challenges when a classifier is to handle real-world data in the presence of imbalanced data and missing values. More specifically, the model performance is very likely to be degraded due to the missing information and the inclination of classifiers to the majority class. To surmount this problem, a natural idea is to use the LNMF model to obtain the desired recovery. Then, for the complete data after imputation, the empirical-feature-space-based switching triple-weight-SMOTE is applied to synthesize safe and correct data (i.e., lie solidly on the region of minority class) to achieve the balance. Such a working principle generates a novel NSS strategy. The proposed NSS strategy has the following obvious merits: 1) the imputation guarantees the similarity to the original dataset; and 2) new synthetic data are safely generated by taking adequate consideration of the information and distribution of datasets. Thus, the proposed NSS can greatly help improve the classification accuracy of real-world datasets.

Was There a 3.5 keV Line?

The 3.5 keV line is a purported emission line observed in galaxies, galaxy clusters, and the Milky Way whose origin is inconsistent with known atomic transitions and has previously been suggested to arise from dark matter decay. We systematically reexamine the bulk of the evidence for the 3.5 keV line, attempting to reproduce six previous analyses that found evidence for the line. We only reproduce one of the analyses; in the other five, we find no significant evidence for a 3.5 keV line when following the described analysis procedures on the original data sets. For example, previous results claimed 4σ evidence for a 3.5 keV line from the Perseus cluster; we dispute this claim, finding no evidence for a 3.5 keV line. We find evidence for background mismodeling in multiple analyses. We show that analyzing these data in narrower energy windows diminishes the effects of mismodeling but returns no evidence for a 3.5 keV line. We conclude that there is little robust evidence for the existence of the 3.5 keV line. Some of the discrepancy of our results from those of the original works may be due to the earlier reliance on local optimizers, which we demonstrate can lead to incorrect results. For ease of reproducibility, all code and data are publicly available.

The promises and pitfalls of disaster aid platforms: a case study of Lebanon’s 3RF

PurposeUsing critical disaster studies and state theory, we assess the disaster aid platform named Lebanon Reconstruction, Reform and Recovery Framework (3RF) that was put in place by international donors in the aftermath of the Beirut Port Blast in August 2020, in order to examine the effectiveness of its inclusive decision-making architecture, as well as its institutional building and legislative reform efforts.Design/methodology/approachThe paper uses the case study approaach and relies on two original data sets compiled by authors, using desk reviews of academic literature and secondary data, in addition to 24 semi-structured expert interviews and participant observation for two years.FindingsThe aid platform appears innovative, participatory and effectively functioning toward recovery and reform. However, in practice, the government dismisses CSOs, undermines reforms and dodges state building, whereas the 3RF is structured in incoherent ways and operates according to conflicting logics, generating inertia and pitfalls that hinder effective participatory governance, prevent institutional building, and delay the making of projects.Research limitations/implicationsThe research contributes to critical scholarship as it addresses an important research gap concerning disaster aid platforms’ institutional design and governance that are under-studied in critical disaster studies and political studies. It also highlights the need for critical disaster studies to engage with state theory and vice-versa.Practical implicationsThe research contributes to evaluations of disaster recovery processes and outcomes. It highlights the limits of disaster aid platforms’ claims for participatory decision-making, institutional-building and reforms.Originality/valueThe paper amplifies critical disaster studies, through the reflexive analysis of a case-study of an aid platform.

Exploring One-Shot Semi-supervised Federated Learning with Pre-trained Diffusion Models

Recently, semi-supervised federated learning (semi-FL) has been proposed to handle the commonly seen real-world scenarios with labeled data on the server and unlabeled data on the clients. However, existing methods face several challenges such as communication costs, data heterogeneity, and training pressure on client devices. To address these challenges, we introduce the powerful diffusion models (DM) into semi-FL and propose FedDISC, a Federated Diffusion-Inspired Semi-supervised Co-training method. Specifically, we first extract prototypes of the labeled server data and use these prototypes to predict pseudo-labels of the client data. For each category, we compute the cluster centroids and domain-specific representations to signify the semantic and stylistic information of their distributions. After adding noise, these representations are sent back to the server, which uses the pre-trained DM to generate synthetic datasets complying with the client distributions and train a global model on it. With the assistance of vast knowledge within DM, the synthetic datasets have comparable quality and diversity to the client images, subsequently enabling the training of global models that achieve performance equivalent to or even surpassing the ceiling of supervised centralized training. FedDISC works within one communication round, does not require any local training, and involves very minimal information uploading, greatly enhancing its practicality. Extensive experiments on three large-scale datasets demonstrate that FedDISC effectively addresses the semi-FL problem on non-IID clients and outperforms the compared SOTA methods. Sufficient visualization experiments also illustrate that the synthetic dataset generated by FedDISC exhibits comparable diversity and quality to the original client dataset, with a neglectable possibility of leaking privacy-sensitive information of the clients.

Design and implementation of an AI-controlled spraying drone for agricultural applications using advanced image preprocessing techniques

PurposeNowadays, food problems are likely to arise because of the increasing global population and decreasing arable land. Therefore, it is necessary to increase the yield of agricultural products. Pesticides can be used to improve agricultural land products. This study aims to make the spraying of cherry trees more effective and efficient with the designed artificial intelligence (AI)-based agricultural unmanned aerial vehicle (UAV).Design/methodology/approachTwo approaches have been adopted for the AI-based detection of cherry trees: In approach 1, YOLOv5, YOLOv7 and YOLOv8 models are trained with 70, 100 and 150 epochs. In Approach 2, a new method is proposed to improve the performance metrics obtained in Approach 1. Gaussian, wavelet transform (WT) and Histogram Equalization (HE) preprocessing techniques were applied to the generated data set in Approach 2. The best-performing models in Approach 1 and Approach 2 were used in the real-time test application with the developed agricultural UAV.FindingsIn Approach 1, the best F1 score was 98% in 100 epochs with the YOLOv5s model. In Approach 2, the best F1 score and mAP values were obtained as 98.6% and 98.9% in 150 epochs, with the YOLOv5m model with an improvement of 0.6% in the F1 score. In real-time tests, the AI-based spraying drone system detected and sprayed cherry trees with an accuracy of 66% in Approach 1 and 77% in Approach 2. It was revealed that the use of pesticides could be reduced by 53% and the energy consumption of the spraying system by 47%.Originality/valueAn original data set was created by designing an agricultural drone to detect and spray cherry trees using AI. YOLOv5, YOLOv7 and YOLOv8 models were used to detect and classify cherry trees. The results of the performance metrics of the models are compared. In Approach 2, a method including HE, Gaussian and WT is proposed, and the performance metrics are improved. The effect of the proposed method in a real-time experimental application is thoroughly analyzed.

A hybrid data fusion approach with twin CNN architecture for enhancing image source identification in IoT environment

AbstractWith the proliferation of digital devices in internet of things (IoT) environment featuring advanced visual capabilities, the task of Image Source Identification (ISI) has become increasingly vital for legal purposes, ensuring the verification of image authenticity and integrity, as well as identifying the device responsible for capturing the original scene. Over the past few decades, researchers have employed both traditional and machine‐learning methods to classify image sources. In the current landscape, data‐driven approaches leveraging deep learning models have emerged as powerful tools for achieving higher accuracy and precision in source prediction. The primary focus of this research is to address the complexities arising from diverse image sources and variable quality in IoT‐generated multimedia data. To achieve this, a Hybrid Data Fusion Approach is introduced, leveraging multiple sources of information to bolster the accuracy and robustness of ISI. This fusion methodology integrates diverse data streams from IoT devices, including metadata, sensor information, and contextual data, amalgamating them into a comprehensive data set for analysis. This study introduces an innovative approach to ISI through the implementation of a Twin Convolutional Neural Network Architecture (TCA) aimed at enhancing the efficacy of source classification. In TCA, the first CNN architecture, referred to as DnCNN, is employed to eliminate noise from the original data set, generating 256 × 256 patches for both training and testing. Subsequently, the second CNN architecture is employed to classify images based on features extracted from various convolutional layers using a 3 × 3 filter, thereby enhancing prediction efficiency. The proposed model demonstrates exceptional accuracy in effectively classifying image sources, showcasing its potential as a robust solution in the realm of ISI.