Hasil untuk "Industries. Land use. Labor"

Julia Manso

Upon taking office in late 2012, Chinese President Xi Jinping launched one of the most intensive anticorruption campaigns in the history of the People's Republic of China. Prior to the campaign, China's land market suffered from corruption, particularly surrounding sale method selection (auction versus listing). Listing is a two-stage sale mechanism that prior research has identified as more susceptible to corruption, leading to lower prices. This paper examines the campaign's impact on land allocation, focusing on whether corruption influences the choice of sale method and, in turn, land sale prices. This paper is the first to utilize Blackwell and Yamauchi (2021, 2024)'s marginal structural model with fixed effects in the inverse probability of treatment weighting model; absorbing time-invariant unobserved confounding and utilizing a set of time-varying covariates as controls, this model can estimate causal effects in the land sale case. I find that indictments in a prefecture cause a statistically significant drop in the probability that land is sold via listing$\unicode{x2014}$an effect that is further compounded when indictments occur in consecutive months. Sensitivity analyses indicate that any violations of the identification assumptions would bias estimates towards zero, confirming the negative effect. A second marginal structural model shows that both mean and median land sale prices increase in the presence of indictments. Together, these results suggest that the anticorruption campaign not only deterred actual corrupt allocation practices, but also impacted the discretionary use of listings.

S. Li, X. Lv, X. Meng et al.

Anap V. N., Gaikar P. S., Jadhav R. M. et al.

This review explores the application of AI technology in agriculture to address challenges such as declining manual labor, limited arable land, and the growing disparity between food production and the increasing global population. AI is presented as a promising solution, with advancements driven by scientists worldwide. Artificial Intelligence (AI) plays a crucial role in optimizing farming practices by analysing data from sensors, satellites, and drones. Applications include monitoring soil health, crop growth, and weather patterns to enhance yields while minimizing resource utilization. AI-powered tools, such as advanced irrigation systems and fertilizer management, ensure efficient use of inputs. The use of robots in agriculture has significantly improved productivity, making farming more efficient and widely adopted. AI techniques offer real-time data, reducing human error and enhancing decision-making. The research highlights that modern AI technology and methods outperform traditional farming methods with minimal human intervention and in a shorter time frame. The review also delves into the development of agricultural robots, highlighting various examples of robots designed for specific tasks within the agricultural industry. The review discusses the challenges faced in applying agricultural robots, particularly the unpredictability of real-world environments. Despite these challenges, it underscores significant advancements in this field and the promising prospects for the future of agricultural robotics.

Wenxin Che, Changhai Qin, Yong Zhao et al.

With rapid economic development and the growing global demand for water resources, the relationship between water demand and economic growth has become a critical international concern. This study investigates the role of water resources in China’s economic growth by extending the Cobb–Douglas production function to include investment, labor, energy, land, and water resources. Using national and regional data from 1949 to 2023, we quantify the spatiotemporal dynamics of factor contributions across primary, secondary, and tertiary industries. Results show that investment remains the dominant growth driver, with rising contributions from energy and land, while labor is increasingly substituted. Water resources exhibit marked industrial and regional heterogeneity: since 2013, water constraints have intensified in the primary sector of the Yellow River basin and Northeast China, and in the secondary sector of the inland northwest and Yellow River provinces. Considering national food security imperatives and given the complementary nature of water–land resources and the fixed nature of land, we propose strategic water network planning based on land productivity patterns to optimize resource coordination and drive high-quality economic development.

Ece Ucar, E. Ertugrul Karsak

The Human Development Index (HDI) introduced by United Nations Development Programme (UNDP) offers a unique quantitative measure that encompasses advancements in three fundamental aspects of human development: health, education, and living standards. However, focusing on only three dimensions when evaluating human development performance of countries is not adequate in today’s digital world. This study proposes a data envelopment analysis (DEA)-based composite index to provide an innovation-integrated human development performance assessment tool for countries. The novel two-stage common-weight DEA-based approach proposed in here is applied in a case study examining the performance assessment of European Union (EU) countries. The first stage of the developed methodology consists of solving the novel commonweight DEA-based approach with HDI indicators as the outputs and the Gini coefficient as the input. At the second stage, innovation-based indicators from World Bank database are used to evaluate innovation efficiency of EU countries. The composite index that yields the complete ranking of EU countries in terms of innovation-integrated human development performance is computed as the product of the efficiency scores resulting from these two stages. The rankings produced by the proposed approach are compared with the HDI rankings as well as the results obtained from various common-weight DEA-based models. First published online 27 November 2025

Viacheslav Davydenko, Anna Kavunska, Viacheslav Barba

The study focuses on the conceptual, theoretical, empirical and methodological foundations of a legal and economic nature, concerning the legal support for the activities of operational units of the National Police in preventing cybercrime, in the context of economic globalisation and existential challenges. Methodology. The present study employed both general and special methods of cognition. Utilising the dialectical method, the author evaluated the essence of countering cybercrime by operational police units in terms of its prevention and prevention of these offences in the legal and economic planes, according to a diverse range of parameters. The analysis established the foundations for a multidimensional study of all the characteristic features of cybercrime prevention in the context of economic integration, in terms of economic and legal etymology. The synthesis established the conditions necessary for the generalisation of the distinctive features of the activities of police operational units. The formal legal method enabled the correct interpretation of the content of legal acts defining the general and special legal regimes of preventive activities of operational police units within the context of economic globalisation and existential challenges. The purpose of the article is to provide a comprehensive analysis of the potential areas for improvement in the activities of the operational units of the National Police in order to prevent cybercrime in the context of economic globalisation and existential challenges. The results of the study demonstrated that the role of the operational units of the National Police in preventing cybercrime in the context of economic globalisation and existential challenges encompasses a range of complex measures in various areas of activity of the relevant police unit, primarily in ensuring cybersecurity. It has been determined that there are specific areas in which the operational units of the National Police can enhance their efforts to combat cybercrime. These areas have been identified in the context of economic globalisation and existential challenges. Conclusion. The advent of cybercrime can be attributed to the prevailing technological transformations in the economy, particularly with regard to the dissemination of information as the primary resource and catalyst for societal advancement. The author's position is that the implementation of economic policies aimed at curbing cybercrime should encompass the following measures: the establishment of a fair and balanced tax system, the formulation of a strategic economic development policy, the promotion of production-oriented initiatives, and the allocation of resources towards the enhancement of public services. From the standpoint of a company's economic security, measures to prevent cybercrime are crucial, due to both local and global economic factors. The analysis of cybercrime legislation enabled the identification of measures of general and special competence taken by the operational units of the National Police. Concurrently, within the legislative framework on national security, which encompasses cybersecurity, the National Police is delineated as a subject of counteraction to such crime, signifying a specialised competence. Concomitantly, the general competence in combating and preventing cybercrime is reflected in the primary function of the National Police, namely to ensure public safety and order, protect human rights and freedoms, the interests of society and the state, and combat crime, including in cyberspace. The primary focus of the implementation of the special competence of operational police units is the Cyber Police Department, which is an integral component of the National Police. The Cyber Police Department is responsible for conducting comprehensive operational and investigative activities as a component of the broader strategy to prevent cybercrime. The authors support the view that the following measures, carried out by operational police units, stand out as effective means of countering cybercrime under conditions of existential challenges associated with armed aggression. These measures include counterintelligence, operational and investigative work, and procedural work to counter relevant information threats; the introduction of incentive measures aimed at creating their own information product; the development of their own information and telecommunications infrastructure; and the establishment of communication between civil society and law enforcement agencies in this area.

Vívian Terra de Azevedo Decúpero, Caroline Damascena Cardoso, Sarah Santos Gomes et al.

Introdução: As universidades públicas desempenham um papel fundamental na produção de conhecimento científico, e por meio da extensão universitária, conectam ensino e pesquisa às necessidades sociais. Nesse contexto, o curso de Farmácia do CCENS-UFES, em parceria com a escola EEEFM Sirena Rezende Fonseca, localizada no distrito de Celina (Alegre-ES), desenvolveu, com o apoio da FAPES, um projeto voltado para a capacitação e conscientização dos alunos do ensino médio sobre Infecções Sexualmente Transmissíveis (IST). A metodologia adotada integrou abordagens teóricas e práticas, com foco em ensaios imunodiagnósticos, permitindo aos estudantes uma aplicação real dos conhecimentos adquiridos. Um dos casos abordados durante o projeto envolveu a história fictícia de Gabriel, aluno do programa de iniciação científica Jr. Gabriel, ao aprender sobre as IST, foi capaz de reconhecer os sinais de uma possível infecção em seu irmão Henrique, que trabalha na roça. Henrique, ao notar uma lesão genital, procurou Gabriel em busca de ajuda. A partir do aprendizado sobre as IST, Gabriel suspeitou da infecção e sugeriu que seu irmão realizasse a bateria de testes rápidos no Centro de Testagem e Aconselhamento de Alegre. O resultado positivo para sífilis evidenciou como a disseminação do conhecimento no âmbito escolar pode ter um impacto direto na saúde e bem-estar da comunidade. Além dessa aplicação prática, observou-se que, ao longo da experiência, muitos alunos demonstraram desconhecimento sobre IST, incluindo sinais, sintomas, modos de transmissão e formas de tratamento. No entanto, houve grande receptividade ao aprendizado, refletida na participação ativa nas atividades laboratoriais e discussões. A evolução na compreensão e na aplicação dos conceitos foi uma das conquistas mais significativas do projeto. Apesar do entusiasmo gerado nas atividades práticas, um dos desafios foi manter o interesse dos alunos durante as exposições teóricas. Para lidar com isso, foram inseridos casos cotidianos, como o mencionado acima, estruturados com narrativas interativas, nas quais os alunos contribuíam com suas próprias soluções para as situações apresentadas. Essa abordagem contribuiu para uma maior imersão no tema e facilitou a assimilação do conteúdo. O alcance do projeto foi limitado pelo número reduzido de alunos atendidos, o que comprometeu sua abrangência. Diante dos resultados, é clara a necessidade de investimentos públicos para ampliar iniciativas como o PICJr, possibilitando a inclusão de mais estudantes e a exploração de outras questões de saúde. A integração entre escolas, universidades e serviços de saúde é fundamental para fortalecer a educação em saúde e incentivar o ingresso no ensino superior, promovendo impactos positivos na formação dos alunos e na comunidade.

Dakota Hester, Vitor S. Martins, Lucas B. Ferreira et al.

Deep learning semantic segmentation methods have shown promising performance for very high 1-m resolution land cover classification, but the challenge of collecting large volumes of representative training data creates a significant barrier to widespread adoption of such models for meter-scale land cover mapping over large areas. In this study, we present a novel label-efficient approach for statewide 1-m land cover classification using only 1,000 annotated reference image patches with self-supervised deep learning. We use the "Bootstrap Your Own Latent" pre-training strategy with a large amount of unlabeled color-infrared aerial images (377,921 patches of 256x256 pixels at 1-m resolution) to pre-train a ResNet-101 convolutional encoder. The learned encoder weights were subsequently transferred into multiple deep semantic segmentation architectures (FCN, U-Net, Attention U-Net, DeepLabV3+, UPerNet, PAN), which were then fine-tuned using very small training dataset sizes with cross-validation (250, 500, 750 patches). Among the fine-tuned models, we obtained 87.14% overall accuracy and 75.58% macro F1 score using an ensemble of the best-performing U-Net models for comprehensive 1-m, 8-class land cover mapping, covering more than 123 billion pixels over the state of Mississippi, USA. Detailed qualitative and quantitative analysis revealed accurate mapping of open water and forested areas, while highlighting challenges in accurate delineation between cropland, herbaceous, and barren land cover types. These results show that self-supervised learning is an effective strategy for reducing the need for large volumes of manually annotated data, directly addressing a major limitation to high spatial resolution land cover mapping at scale.

Han Ke, Xiao Ke, Ye Yan et al.

DL based Synthetic Aperture Radar (SAR) ship detection has tremendous advantages in numerous areas. However, it still faces some problems, such as the lack of prior knowledge, which seriously affects detection accuracy. In order to solve this problem, we propose a scene-aware SAR ship detection method based on unsupervised sea-land segmentation. This method follows a classical two-stage framework and is enhanced by two models: the unsupervised land and sea segmentation module (ULSM) and the land attention suppression module (LASM). ULSM and LASM can adaptively guide the network to reduce attention on land according to the type of scenes (inshore scene and offshore scene) and add prior knowledge (sea land segmentation information) to the network, thereby reducing the network's attention to land directly and enhancing offshore detection performance relatively. This increases the accuracy of ship detection and enhances the interpretability of the model. Specifically, in consideration of the lack of land sea segmentation labels in existing deep learning-based SAR ship detection datasets, ULSM uses an unsupervised approach to classify the input data scene into inshore and offshore types and performs sea-land segmentation for inshore scenes. LASM uses the sea-land segmentation information as prior knowledge to reduce the network's attention to land. We conducted our experiments using the publicly available SSDD dataset, which demonstrated the effectiveness of our network.

Prarthana P. Kartholy, Thandi M. Labor, Neil N. Panchal et al.

Selecting a college major is a difficult decision for many incoming freshmen. Traditional academic advising is often hindered by long wait times, intimidating environments, and limited personalization. AI Chatbots present an opportunity to address these challenges. However, AI systems also have the potential to generate biased responses, prejudices related to race, gender, socioeconomic status, and disability. These biases risk turning away potential students and undermining reliability of AI systems. This study aims to develop a University of Maryland (UMD) A. James Clark School of Engineering Program-specific AI chatbot. Our research team analyzed and mitigated potential biases in the responses. Through testing the chatbot on diverse student queries, the responses are scored on metrics of accuracy, relevance, personalization, and bias presence. The results demonstrate that with careful prompt engineering and bias mitigation strategies, AI chatbots can provide high-quality, unbiased academic advising support, achieving mean scores of 9.76 for accuracy, 9.56 for relevance, and 9.60 for personalization with no stereotypical biases found in the sample data. However, due to the small sample size and limited timeframe, our AI model may not fully reflect the nuances of student queries in engineering academic advising. Regardless, these findings will inform best practices for building ethical AI systems in higher education, offering tools to complement traditional advising and address the inequities faced by many underrepresented and first-generation college students.

Xiaoli Chen, Zhefeng Huang, Chaoguang Luo et al.

The improvement in urban production efficiency has led to income distribution being skewed towards urban labor, thereby widening the urban–rural income gap. However, integration of the agricultural industry at the county level can accelerate the flow of production factors between industries. Therefore, this study evaluates the degree of agricultural industry integration at the county level using the entropy weight method and explores its impact on the urban–rural income gap, based on sample data from 1122 counties in China spanning from 2014 to 2021. The research findings reveal the following: (1) The fixed model demonstrates that enhancing agricultural industry integration can significantly narrow the urban–rural income gap; (2) The mediating model indicates that this narrowing effect can be achieved by improving the green total factor productivity of agriculture; (3) Regional heterogeneity analysis indicates that the impact of agricultural industry integration is more pronounced in the central region and main crop production areas; (4) The results of the spatial Durbin model demonstrate that agricultural industry integration also exhibits a significant positive spatial spillover effect on neighboring areas. The outcomes of this study contribute to enriching the research on agricultural industry integration for green and low-carbon agricultural development, further promoting the development of county-level agricultural industry integration, and providing valuable insights for other similar countries.

Andi Nur Cahyo, Ying Dong, Taryono et al.

Agroforestry is often seen as a sustainable land-use system for agricultural production providing ecosystem services. Intercropping with food crops leads to equal or higher productivity than monoculture and results in food production for industry and subsistence. Low rubber price and low labor productivity in smallholdings have led to a dramatic conversion of rubber plantations to more profitable crops. The literature analysis performed in this paper aimed at better understanding the ins and outs that could make rubber-based agroforestry more attractive for farmers. A comprehensive search of references was conducted in March 2023 using several international databases and search engines. A Zotero library was set up consisting of 415 scientific references. Each reference was carefully read and tagged in several categories: cropping system, country, main tree species, intercrop type, intercrop product, level of product use, discipline of the study, research topic, and intercrop species. Of the 232 journal articles, 141 studies were carried out on rubber agroforestry. Since 2011, the number of studies per year has increased. Studies on rubber-based agroforestry systems are performed in most rubber-producing countries, in particular in Indonesia, Thailand, China, and Brazil. These studies focus more or less equally on perennials (forest species and fruit trees), annual intercrops, and mixed plantations. Of the 47 annual crops associated with rubber in the literature, 20 studies dealt with rice, maize, banana, and cassava. Agronomy is the main discipline in the literature followed by socio-economy and then ecology. Only four papers are devoted to plant physiology and breeding. The Discussion Section has attempted to analyze the evolution of rubber agroforestry research, progress in the selection of food crop varieties adapted to agroforestry systems, and to draw some recommendations for rubber-based agroforestry systems associated with food crops.

Kostiantyn Fuks

The purpose of this article is to provide a comprehensive examination of the informational and organisational capabilities of marketing activities in the market for digital products and services. It highlights the importance of data analysis, web analytics and technology partnerships for success in the digital marketplace. It also examines modern organisational strategies to help IT companies effectively implement marketing initiatives and adapt quickly to changing business landscapes. Methodology. This article is based on a theoretical and methodological review of the existing scientific literature on digital technologies, the marketing of digital products and services, and an overview of current technological and organisational solutions in the digital field. In addition, it includes a survey of marketing managers from renowned IT companies with the aim of delineating the typology of organisational structures within marketing departments. Results. Information delivery, data analytics, monitoring tools and web analytics are critical to digital marketing in IT organisations, facilitating the collection and analysis of data from multiple sources such as websites, social media and CRM systems. By leveraging big data and machine learning algorithms, it is possible to identify complex dependencies and predict consumer behaviour. Technological partnerships and collaborations with startups are becoming increasingly important for IT companies' marketing efforts, providing access to fresh ideas, technologies and a competitive edge. Organisational structures in the marketing departments of IT companies emphasise agility and cross-functional teamwork, often using agile methodologies. This promotes adaptability to market changes. Marketing structures typically include inbound approaches, flexible growth-oriented setups, and streamlined hierarchies. Practical implications. These marketing tools and organisational methods are recommended for implementation in the marketing departments of IT companies. The correlation between informational and organisational capabilities contributes to the achievement of marketing goals and the competitive advantage of IT companies in the marketplace. Scrum and Kanban, widely used agile frameworks, are not limited to technology companies but are also common in financial services and retail. Value / Оriginality. In the context of the ongoing military conflict, successful operation of Ukrainian IT companies in the modern world requires not only technological superiority, but also effective marketing and a well-organised internal structure. To accelerate the recovery of the Ukrainian IT sector and improve existing practices, the following recommendations have been made.

Sanjeet S. Kaintura, Swati Thakur, Sarabjot Kaur et al.

In this work, radioactivity investigations of soil samples from neutral and agricultural sites in Punjab/India have been carried out to study the impact of land use patterns. The analysis of radiological, mineralogical, physicochemical, and morphological attributes of soil samples has been performed employing state-of-the-art techniques. The mean activity concentration of 238U, 232Th, 40K, 235U, and 137Cs, measured using a carbon-loaded p-type HPGe detector, in neutral land was observed as 58.03, 83.95, 445.18, 2.83, and 1.16Bq kg-1, respectively. However, in vegetation land, it was found to be 40.07, 64.68, 596.74, 2.26 and 2.11Bq kg-1, respectively. In the detailed activity analysis, radium equivalent (Raeq) radioactivity is found to be in the safe prescribed limit of 370Bq kg-1 for all investigated soil samples. However, the dosimetric investigations revealed that the outdoor absorbed gamma dose rate (96.08nGy h-1) and consequent annual effective dose rate (0.12mSv y-1) for neutral land, and the gamma dose rate (82.46nGy h-1) and subsequent annual effective dose rate (0.10mSv y-1) for vegetation land marginally exceeded the global average. The surface morphology of neutral land favored more compactness, while agricultural land favored high porosity. Various heavy metals of health concern, namely As, Cd, Co, Cr, Cu, Hg, Pb, Se, and Zn, were also evaluated in all soil samples using Inductively Coupled Plasma-Mass Spectroscopy (ICP-MS). Pollution Load Index (PLI) and Ecological Risk Index (RI) revealed that vegetation land was more anthropogenically contaminated than neutral land, with maximum contamination from Hg and As.

Venkat Ram Reddy Ganuthula

This paper introduces Agency-Driven Labor Theory as a new theoretical framework for understanding human work in AI-augmented environments. While traditional labor theories have focused primarily on task execution and labor time, ADLT proposes that human labor value is increasingly derived from agency - the capacity to make informed judgments, provide strategic direction, and design operational frameworks for AI systems. The paper presents a mathematical framework expressing labor value as a function of agency quality, direction effectiveness, and outcomes, providing a quantifiable approach to analyzing human value creation in AI-augmented workplaces. Drawing on recent work in organizational economics and knowledge worker productivity, ADLT explains how human workers create value by orchestrating complex systems that combine human and artificial intelligence. The theory has significant implications for job design, compensation structures, professional development, and labor market dynamics. Through applications across various sectors, the paper demonstrates how ADLT can guide organizations in managing the transition to AI-augmented operations while maximizing human value creation. The framework provides practical tools for policymakers and educational institutions as they prepare workers for a labor market where value creation increasingly centers on agency and direction rather than execution.

Andrew Ireland, David Johnston, Rachel Knott

We use daily longitudinal data and a within-worker identification approach to examine the impacts of heat on labor force dynamics in Australia. High temperatures during 2001-2019 significantly reduced work attendance and hours worked, which were not compensated for in subsequent days and weeks. The largest reductions occurred in cooler regions and recent years, and were not solely concentrated amongst outdoor-based workers. Financial and Insurance Services was the most strongly affected industry, with temperatures above 38°C (100°F) increasing absenteeism by 15 percent. Adverse heat effects during the work commute and during outdoor work hours are shown to be key mechanisms.

Meng Tang, Shiwei Ma, Jianzheng Xu et al.

Chemical looping gasification (CLG) of biomass produces high contents of syngas, which would have inhibition effect on the gasification of its biomass char. Experiments using a rice husk char as fuel and a low-cost red mud as oxygen carrier for CLG investigation were performed, and effects of temperature, concentrations of steam and H2 on gasification rate were evaluated. Meanwhile, the mathematical models coupling with reaction and diffusion were established focusing on the H2 inhibition on syngas distributions inside and surrounding a single char particle. The results indicated that H2 in the reaction atmosphere has an inhibition effect on its char conversion, and at a high temperature the inhibition effect tends to be stronger. The shrinking core model (spherical symmetry) was found to be suitable to describe the char conversion under the present conditions with the reaction kinetic parameters of E = 128.8 kJ mol−1 and A = 451.2 s−1. In the internal diffusion of a single char particle, the concentrations of CO and H2 both decrease with the increase of dimensionless radius due to the consumption of carbon. In the external diffusion of the char particle, the concentrations of CO and H2 decrease with the increase of the dimensionless radius. The accumulation of H2 inside the char particle prevents CO production, thus inhibiting char gasification.

Mobayode O. Akinsolu, Khalil Zribi

In this paper, the growing significance of data analysis in manufacturing environments is exemplified through a review of relevant literature and a generic framework to aid the ease of adoption of regression-based supervised learning in manufacturing environments. To validate the practicality of the framework, several regression learning techniques are applied to an open-source multi-stage continuous-flow manufacturing process data set to typify inference-driven decision-making that informs the selection of regression learning methods for adoption in real-world manufacturing environments. The investigated regression learning techniques are evaluated in terms of their training time, prediction speed, predictive accuracy (R-squared value), and mean squared error. In terms of training time (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>T</mi><mi>T</mi></mrow></semantics></math></inline-formula>), <i>k</i>-NN20 (<i>k</i>-Nearest Neighbour with 20 neighbors) ranks first with average and median values of 4.8 ms and 4.9 ms, and 4.2 ms and 4.3 ms, respectively, for the first stage and second stage of the predictive modeling of the multi-stage continuous-flow manufacturing process, respectively, over 50 independent runs. In terms of prediction speed (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>P</mi><mi>S</mi></mrow></semantics></math></inline-formula>), DTR (decision tree regressor) ranks first with average and median values of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>5.6784</mn><mo>×</mo><msup><mn>10</mn><mn>6</mn></msup></mrow></semantics></math></inline-formula> observations per second (ob/s) and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>4.8691</mn><mo>×</mo><msup><mn>10</mn><mn>6</mn></msup></mrow></semantics></math></inline-formula> observations per second (ob/s), and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>4.9929</mn><mo>×</mo><msup><mn>10</mn><mn>6</mn></msup></mrow></semantics></math></inline-formula> observations per second (ob/s) and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>5.8806</mn><mo>×</mo><msup><mn>10</mn><mn>6</mn></msup></mrow></semantics></math></inline-formula> observations per second (ob/s), respectively, for the first stage and second stage of the predictive modeling of the multi-stage continuous-flow manufacturing process, respectively, over 50 independent runs. In terms of R-squared value (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula>), BR (bagging regressor) ranks first with average and median values of 0.728 and 0.728, respectively, over 50 independent runs, for the first stage of the predictive modeling of the multi-stage continuous-flow manufacturing process, and RFR (random forest regressor) ranks first with average and median values of 0.746 and 0.746, respectively, over 50 independent runs, for the second stage of the predictive modeling of the multi-stage continuous-flow manufacturing process. In terms of mean squared error (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>M</mi><mi>S</mi><mi>E</mi></mrow></semantics></math></inline-formula>), BR (bagging regressor) ranks first with average and median values of 2.7 and 2.7, respectively, over 50 independent runs, for the first stage of the predictive modeling of the multi-stage continuous-flow manufacturing process, and RFR (random forest regressor) ranks first with average and median values of 3.5 and 3.5, respectively, over 50 independent runs, for the second stage of the predictive modeling of the multi-stage continuous-flow manufacturing process. All methods are further ranked inferentially using the statistics of their performance metrics to identify the best method(s) for the first and second stages of the predictive modeling of the multi-stage continuous-flow manufacturing process. A Wilcoxon rank sum test is then used to statistically verify the inference-based rankings. <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>D</mi><mi>T</mi><mi>R</mi></mrow></semantics></math></inline-formula> and <i>k</i>-NN20 have been identified as the most suitable regression learning techniques given the multi-stage continuous-flow manufacturing process data used for experimentation.

Romulus Costache, Hazem Ghassan Abdo, Arun Pratap Mishra et al.

AbstractIn this work, the vulnerability to flooding in the Prahova River basin was calculated and analyzed using advanced methods and techniques. Thus, 2 hybrid models represented by Iterative Classifier Optimizer – Multiclass Alternating Decision Tree – Certainty Factor (ICO-LADT-CF) and Fuzzy-Analytical Hierarchy Process – Certainty Factor (FAHP-CF) were generated, which had as input data the values of 10 flood predictors and a number of 158 points where historical floods occurred. In the first step, the Certainty Factor values were calculated, which were then used in the Fuzzy-Analytical Hierarchy Process and Multiclass Alternating Decision Tree models. It should be mentioned that the Multiclass Alternating Decision Tree model was optimized with the help of the Iterative Classifier Optimizer. In the case of both ensemble models the slope angle was the most important flood conditioning factor. Moreover, according to Certainty Factor modelling the 8 classes/categories achieved the maximum value of 1. Next, the susceptibility to floods on the surface of the study area was derived. On average, about 20% of the study area has areas with high and medium susceptibility to flash floods. After evaluating the quality of the models through Receiver Operating Characteristics (ROC) Curve, the following results emerged: Success Rate for Flood Potential Index (FPI) Iterative Classifier Optimizer – Multiclass Alternating Decision Tree – Certainty Factor (ICO-LADT-CF) (Area Under Curve = 0.985) and Flood Potential Index (FPI) Fuzzy-Analytical Hierarchy Process – Certainty Factor (FAHP-CF) (Area Under Curve = 0.967); Prediction Rate for Flood Potential Index (FPI) Iterative Classifier Optimizer – Multiclass Alternating Decision Tree – Certainty Factor (ICO-LADT-CF) (Area Under Curve = 0.952) and Flood Potential Index Fuzzy-Analytical Hierarchy Process – Certainty Factor (FAHP-CF) (Area Under Curve = 0.913). At the same time, the accuracies of the models were: Training dataset − 0.943 (Iterative Classifier Optimizer – Multiclass Alternating Decision Tree – Certainty Factor) and 0.931 (Fuzzy-Analytical Hierarchy Process – Certainty Factor); Validating dataset − 0.935 (Iterative Classifier Optimizer – Multiclass Alternating Decision Tree – Certainty Factor) and 0.926 (Fuzzy-Analytical Hierarchy Process – Certainty Factor). As main conclusion, it can be mentioned that the 2 ensemble models outperform the previous machine learning models applied on the same study area before.

Rocío Joo, Gavin McDonald, Nathan Miller et al.

Many fishing vessels use forced labor, but identifying vessels that engage in this practice is challenging because few are regularly inspected. We developed a positive-unlabeled learning algorithm using vessel characteristics and movement patterns to estimate an upper bound of the number of positive cases of forced labor, with the goal of helping make accurate, responsible, and fair decisions. 89% of the reported cases of forced labor were correctly classified as positive (recall) while 98% of the vessels certified as having decent working conditions were correctly classified as negative. The recall was high for vessels from different regions using different gears, except for trawlers. We found that as much as ~28% of vessels may operate using forced labor, with the fraction much higher in squid jiggers and longlines. This model could inform risk-based port inspections as part of a broader monitoring, control, and surveillance regime to reduce forced labor. * Translated versions of the English title and abstract are available in five languages in S1 Text: Spanish, French, Simplified Chinese, Traditional Chinese, and Indonesian.