Search

Global Grand Challenges (GCs) have received only a limited attention within the tourism literature and this Progress paper examines one such GC – dementia and the contribution that tourism research can make to helping people live well with dementia. The paper critically debates the concept of GCs, the challenges of addressing them and how dementia presents both a challenge and opportunity for the academy. Using the concept of the visitor journey and the social model of disability as a paradigm, the paper reviews progress towards creating a more dementia-inclusive society through the auspices of tourism research, reviewing the contributions to date and where the interconnections with dementia and tourism exist. The review draws from a wide interdisciplinary framework including health, medicine, travel medicine and leisure and argues for a greater use of transdisciplinary approaches to address GCs. [ABSTRACT FROM AUTHOR]

This paper examines the characteristics that drive conflicting outcomes on the impact of Twitter data on firm returns using financial micro data. Using 314 European tourism firms as a case study and a sample of 63 million Tweets, we build sentiment and emotion (anger, fear, joy) data series and use them to compute impulse response functions for firm returns. Our results indicate that firm size and popularity are the most important firm features that explain the asymmetric impact of Twitter sentiment and of the anger emotion, while debt explains the variations in the impact of the fear emotion. We also find that the impact of the joy emotion is more evident before the COVID-19 pandemic and more muted after the outbreak. Our findings reconcile varied research on Twitter's impact on tourism industry returns and provide insights to practitioners on using Twitter to gauge online users' collective knowledge of real outcomes. [ABSTRACT FROM AUTHOR]

Authenticity is one of the central components of the tourist experience and has been the subject of substantial academic research. Despite this attention, debate on the notion is ongoing. This paper aims to enhance the analytic potential of the largely Western-centric notion of authenticity by examining the value and meaning of Suzhou food authenticity, from the perspective of producers and suppliers of food and food tourism experiences. Using semi-structured interviews, participant observation and documentary analysis, this study finds that the broad notion of authenticity has considerable relevance to supply-side stakeholders' perceptions of food tourism experiences in Suzhou, however in describing certain foods, local stakeholders do not use a term that directly translates to "authentic", and instead rely on many other Chinese concepts and expressions to authenticate food attractions and experiences. This study confirms the significance of authenticity to food tourism experiences from the producer and supplier perspective but also suggests that authenticity is a culturally specific notion and, fundamentally, there is great utility in applying a constructivist epistemology to study the Chinese concepts of authenticity. [ABSTRACT FROM AUTHOR]

This paper examines the reasons why many people are reticent about travelling in a COVID-adapted world. It reports on a study of residents of Southeast Queensland, Australia conducted in mid-2022, up to six months after borders reopened after a prolonged COVID-19 shutdown. About one quarter of respondents were less interested in travel in a COVID-adapted world than they were before the pandemic struck. They were a diverse group whose reasons for their reticence could be categorised into four broad risk groups of: ongoing anxiety; fear of catching the disease; satisfaction risk, and; travel risk as reflected by an overall loss of interest in travel. Each group displayed different COVID-adapted travel patterns that reflect the operationalisation of different risk categories. A follow-up survey conducted in August 2023 confirmed that up to one in four people still have less desire to travel as a result of COVID-19. [ABSTRACT FROM AUTHOR]

The recent surge in scale development studies within tourism research necessitates a critical reevaluation of our approach to construct operationalization. This paper addresses a gap in the literature by posing a fundamental question: what is the intended purpose of the scale we are developing or using? By explicitly considering this question, researchers can make informed decisions about the most appropriate measurement model option. This article presents three common research objectives, each guiding researchers towards the most suitable modelling approach. Additionally, the article offers practical guidance on avoiding common pitfalls in scale development. This framework benefits both early-career researchers new to latent variable modelling and experienced researchers seeking to refine their approach to scale development and construct operationalization. [ABSTRACT FROM AUTHOR]

The impacts of wildfires on tourism are growing, with concomitant detrimental consequences for tourists and destinations. However, only a few studies have assessed wildfires in tourism-dependent regions, and none have systematically explored fire risks. This paper summarizes the academic literature on tourism and wildfires that serves as a background for developing a tourism fire exposure index. The index identifies regions in the European Union at the NUTS2 level with high wildfire risks and high tourism dependency. Results show that exposure is exceptionally high in regions of Portugal and Mediterranean islands belonging to Greece and Spain. As vulnerabilities can be strategically reduced through adaptation, findings serve as a basis for the development of an integrated wildfire management framework for exposed destinations. [ABSTRACT FROM AUTHOR]

The froghopper extinct family Sinoalidae shows high paleo-diversity in mid-Cretaceous Kachin amber biota. The sinoalid genus Cretadorus Chen, 2020 is revised in this study. Araeoanasillus Poinar et Brown, 2023, tentatively placed in Sinoalidae with subfamily and tribe incertae sedis in original paper, is proposed herein to be synonymized under Cretadorus , leading to Cretadorus leptosomus (Poinar et Brown, 2023) comb. nov. A new species of this genus, Cretadorus qingyui sp. nov., is described and illustrated on the basis of an almost complete fossil trapped in Kachin amber. The Gondwanan origin of Burma Terrane suggests that Sinoalids in Kachin amber are likely one of residual groups of Gondwanan biotae, and so this family had wide paleobiogeographic distribution on the earth in the Jurassic. In the Early Cretaceous, the distribution range of Sinoalidae has reduced: it at least probably disappeared in northeastern Eurasia. This hemipteran lineage was extinct in the late Mesozoic owing to food crisis after the angiosperm floristic revolution. [ABSTRACT FROM AUTHOR]

Droplet impingement on leaf surfaces is a common phenomenon in the spray application process. Most impingements have focused on droplet deposition behavior on stationary leaf surfaces. However, airflow movement and auxiliary airflow during the spray application process create disturbances and generate vibrations on the leaves, which would inevitably affect the deposition conditions of droplets on leaf surfaces. A three-dimensional "droplet-leaf vibration" Computational fluid dynamics (CFD) simulation model is constructed in this paper, and model validation and simulation tests are performed to investigate the effects of leaf vibration on droplet deposition. Experimental results reveal that when the droplet velocity is 1 m/s, with a 60° inclination angle and a vibrational angular velocity of 9 rad/s, the spreading area factor of a 200-μm droplet has the greatest increase up to a value of 1.34, and vibrational effects on the deposition behavior of the three droplet diameters demonstrate a consistent trend. Compared to stationary leaves, vibrating wheat leaves can alter the impingement behavior of droplets close to critical conditions, and vibration can also increase the sliding range for droplets. Vibration in wheat leaves can promote droplet spreading and deposition and increase the spreading area of droplets on the leaf surface. The effects of vibration on large-diameter droplets are more significant compared to small-diameter droplets, where droplet spreading and movement can be effectively enhanced. This paper shall provide a three-dimensional "droplet-leaf vibration" CFD simulation method, providing novel research ideas for the study of droplet deposition behavior on vibrating leaves. • Constructed a three-dimensional "droplet-leaf vibration" CFD simulation model. • Leaf vibration alters the droplet impingement behavior. • The spreading area on the leaf surface increases due to leaf vibration. • The effect of vibration on low-velocity or large droplets is more significant. • However, a risk of slip loss exists at high inclination angles. [ABSTRACT FROM AUTHOR]

The presence of straw on the soil is crucial for enhancing its physical, chemical, and biological conditions in no-tillage cropping systems, while contributing to weed control. This study aimed to determine the optimal spray volume for desiccating ground cover plants using glyphosate applied by an unmanned aerial vehicle (UAV). Treatments included an untreated control and glyphosate spraying at 5, 10, 15, 20, and 25 L ha−1 spray solution. The study was conducted in three fields in the State of Paraná, Brazil. Spraying variables were assessed using water-sensitive paper and the e-Sprinkle software, and included, covered area (%), recovered spray volume (L ha−1), droplet impact density, coefficient of variation for droplet diameter (CV%), and relative amplitude (SPAN). Herbicidal efficacy and dry biomass of cover plants were also evaluated. Increasing spray volume improved covered area, recovered volume, droplet impact density, and droplet diameter-spectrum variation but had no effect on droplet spectrum homogeneity, control of black oat (Avena strigosa), turnip (Raphanus sativus), or buckwheat (Fagopyrum esculentum). Spray volumes ranging from 5.0 to 25 L ha−1, applied with a UAV, provided satisfactory desiccation percentages of ground cover plants irrespective of species or location. Thus, for desiccating ground cover plants with glyphosate applied by UAV, a volume as low as 5.0 L ha−1 is effective. • There is influence of spray volume for drying plants for soil cover with glyphosate sprayed by drone? • The glyphosate herbicide spraying for drying with spray volumes of 5, 10, 15, 20 and 25 L ha−1. • The experiment was replicated in three farmers in the Paraná state, Brazil. • The variables evaluated were: spray quality, control of plants and their dry mass. • Spray volumes from 5.0 to 25 L ha−1 applied with drone provided satisfactory levels of control of ground cover plants. [ABSTRACT FROM AUTHOR]

In sub-Saharan Africa, agricultural intensification and urbanization have increased the risk of proliferation of rodents in rural and urban habitats. Management of rodent populations is a challenge in terms of food security and public health. However, conventional efforts to manage rodents are currently reactive and based on the inadequate use of synthetic chemical rodenticides, including first- and second-generation anticoagulants and acute rodenticides. This approach carries substantial environmental and health risks and has yielded limited success in terms of reduction of rodent populations sustainably. In this paper, which is the second part of a diptych, we advocate for a shift towards more sustainable and environmentally friendly approaches, such as Ecologically-Based Rodent Management (EBRM), as a realistic alternative to synthetic rodenticides. This method is based on a good knowledge of habitat use, species diversity and population dynamics of major rodent pests, and involves community-based interventions aimed at reducing rodent abundance to economically and hygienically acceptable levels in the long term. We present for the first time a comprehensive compilation of published and unpublished information derived from observational field studies conducted in Ethiopia, Niger, Nigeria, Benin, Mali, Mauritania and Senegal with the aim to provide an overview of EBRM case studies in these countries of sub-Saharan Africa. This paper intends to serve as a catalyst for change, encouraging the transformation of rodent management practices towards sustainable methods. We aim at stimulating further research and interventions that promote EBRM in Africa, ultimately fostering more environmentally conscious and effective solutions. [Display omitted] • In Africa, agricultural intensification and urbanization are major changes. • These changes increase the risk of rodent proliferation in rural and urban habitats. • Conventional rodent control relies on reactive, inappropriate use of rodenticides. • Ecologically-Based Rodent Management has been poorly tested in sub-Saharan Africa. • This method can be a realistic, sustainable and environment-friendly alternative. [ABSTRACT FROM AUTHOR]

Rhamphicarpa fistulosa (Hochst.) Benth., is a facultative parasitic plant causing persistent weed problems in smallholder rice crops across Africa. It was first identified as a rice weed in the 1990's in West Africa. The objective of this review was to comprehensively inform the crop protection research community and extension services on the newly gained insights on R. fistulosa since the last review in 2014. Following a systematic literature search in Web of Science on papers published after September 2014, the cut-off date of the last review, the resulting publications are reviewed. Parasitizing Rhamphicarpa fistulosa plants gain considerably in biomass and reproductive output, compared to independently growing plants. The host incurs severe reductions in photosynthetic efficiency and biomass production. Host-plant assimilates primarily benefit parasite growth and reproduction. Rice yield losses caused by R. fistulosa infestations range from 24 to 73% depending on infestation density and cultivar. Annual crop losses in sub-Saharan Africa were estimated at 204,000 tons of milled rice, with associated annual economic losses of US $82M, affecting >140,000 rural households. Rice cultivars NERICA-L-40 and -31 were identified as resistant and high yielding under R. fistulosa infested conditions. Early sowing decreases R. fistulosa infection. Contrary to the obligate parasitic weed Striga spp., the facultative R. fistulosa is not controlled by fertilisers. The past decade of research generated valuable insights in the genetics, germination biology, environmental and ecological contexts, distribution and impacts on crop yields and economies, and disclosed feasible management options. • Rice vampireweed (Rhamphicarpa fistulosa) is a facultative parasitic weed on rice in Africa. • We reviewed the literature since the last review, ten years ago, to report on research progress. • The weed affects >140,000 farm households and causes losses to African economies worth US $82 M/year. • Control recommendations include identified resistant and tolerant rice cultivars and early sowing. • Small rice production improvements from fertilisers, trade-off with strong weed biomass increments. [ABSTRACT FROM AUTHOR]

• A comprehensive evaluation system for park recreational services is proposed. • Urban parks recreational services exhibit spatial clustering. • Community parks are crucial in promoting overall spatial equity of urban parks. • It is necessary to limit the size of regional parks in a compact city. • Recreational environment quality equity surpasses recreational opportunity equity. Spatial equity in urban park recreational services can significantly contribute to sustainable urban planning. However, there are shortcomings in research comparing the spatial equity of different categories of parks and urban parks overall from the perspective of recreational opportunities and recreational environment quality available to residents across various neighborhoods. In this paper, emphasizing park access within a 10-minute walk, we proposed an evaluation system at the neighborhood level for regional parks, community parks, and urban parks overall (regional and community parks combined) from this under-researched perspective. Taking Singapore as a case study, the feasibility of this evaluation system has been verified. We applied Lorenz curve, Gini coefficient, locational entropy, and spatial autocorrelation analysis to compare the differences of horizontal spatial equity and spatial distribution patterns of different categories of parks and urban parks overall from the perspective of recreational opportunities and recreational environment quality. Results showed that the horizontal spatial inequity of recreational opportunities is higher than that of recreational environment quality with respect to regional parks, community parks, and urban parks overall. Compared with regional parks, community parks have a greater effect on improving the horizontal spatial equity of recreational opportunities and recreational environment quality of urban parks overall. Park recreational opportunities and recreational environment quality available to residents in each neighborhood have significant spatial accumulation patterns. The evaluation system and its application enable a more comprehensive assessment of the spatial distribution of neighborhood-level park recreational opportunities and recreational environment quality. [ABSTRACT FROM AUTHOR]

• M2MHub tool uses MCDA and GIS to support planning of shared mobility hubs. • Criteria are selected considering hubs as places for seamless multimodal transfers. • Weights of location criteria and sub-criteria in urban areas are calculated by AHP. • The model is applied to Barcelona to create heat maps of desirable locations. • The tool could help administrations and operators to achieve sustainable mobility. In the move towards sustainable urban mobility through seamless intermodality, European cities are faced with the possibility of implementing shared mobility systems. They constitute an opportunity to create new urban hubs, considered as nodes of intermodality and places of urban intensity. In order to effectively plan the future locations of shared mobility hubs, this paper outlines the methodological framework that sustains the design of a new decision-support tool, the so-called Mcda2MobilityHub (M2MHub) , 1 1 Link to the M2MHub tool, which is available as an open plugin for QGIS: https://github.com/natrouk/Mcda2MobilityHub-desicion-support-tool%5fQGIS-plugin. using Multi-Criteria Decision Analysis (MCDA) and Geographic Information Systems (GIS). For this purpose, the analysis of existing literature and interviews with local authorities and transport operators, led to the identification of six main location criteria (mobility, compactness, diversity of uses, profile of potential users, spatial configuration and environment). The criteria weights were calculated using the Analytic Hierarchy Process (AHP) and the framework was applied to the case study of the city of Barcelona. The results obtained are presented in the form of heat maps, highlighting the flexibility of the decision-support tool to transform open data into appropriate indicators and detailed maps. This output can be used to support future policies for planning shared mobility hubs as places for convenient multimodal transfers, which also enable social activities and improve the quality of life in European cities. [ABSTRACT FROM AUTHOR]

Urban energy transition is a multifaceted phenomenon encompassing political dynamics, governance structures, and technological innovations. This paper explores the intersection of these elements, focusing on renewable energy integration, grid stability, and resilience metrics as key components in urban networks. Through a comprehensive analysis, we investigate the implications of these factors on sustainable urban development. Our findings underscore the importance of effective policies, technological advancements, and social equity in shaping the future of urban energy systems. The study provides valuable insights for policymakers, researchers, and practitioners engaged in fostering sustainable urban futures. • Studying political, economic, technological, and social aspects of urban development. • Investigating urban energy transition, and contributing insights for sustainable urban development. • Assessing the interplay between regulatory frameworks and renewable energy integration. [ABSTRACT FROM AUTHOR]

• More than 200 indicators of 3D urban morphology were extracted and reviewed. • Multiscale network analysis was conducted to reveal the indicator usage patterns. • The hierarchy, preferences and hybrid mesoscale patterns of indicators were found. • Interdisciplinary frameworks were established to provide references for indicators. Intense and rapid urbanization is accompanied by expansion, with both planar and height changes in the urban landscape influencing urban energy consumption, local climate, and sustainable development. As essential components for quantitatively analyzing urban morphology, many indicators have been introduced and adopted for practical studies, presenting a complicated and pluralistic usage pattern, which may also weaken comparability and compatibility. Inspired by co-citation networks, we reviewed 92 relevant papers and summarized more than 200 indicators through network analysis to reveal and clarify the multiscale usage and interaction patterns of the indicators. With reference to theoretical and methodological sources, we divided the various indicators into five categories: landscape metrics, surface metrics, urban canopy parameters, building metrics, and other metrics. The indicators currently used have the following characteristics. First, numerous indicators exhibit a strong hierarchy and interconnected heterogeneity in the network. Some core indicators (e.g., mean height and percentage of landscape) occupy the central positions of the network, and node strength follows a power-law distribution. Second, different indicator types have distinct preferences for describing targets and terminology, and applying topics. Relatively few indicators have focused on vegetation, and the application of these indicators is primarily prevalent in the domain of environmental research. Third, the indicator network has a hybrid mesoscale structure combining core-periphery and community structures, which correspond to mainstream indicators governed by core and nascent indicators, respectively. Finally, we conclude that multidisciplinary indicators form an overlapping, developing, and integrated framework for quantifying the three-dimensional morphology of cities, which is expected to provide a systematic summary and reference for the indicators for urban morphology analysis. [ABSTRACT FROM AUTHOR]

• Seasonal patterns of SUHII worldwide are classified into five typical patterns. • Same seasonal patterns between DNC and daytime SUHII account for 80% globally. • Seasonal patterns of daytime SUHII indicate opposite seasonal variations to ∆EVI. • Daytime SUHII is corresponded to the opposite patterns to LHF but similar to NSR. Variations and controls of surface urban heat island (SUHI) drawn great attention since its close association with environmental issues and heat risk. However, three issues remained neglect, namely, the mismatch and insignificant variations, seasonal patterns for SUHII DNC (day-and-night contrast) and impacts from surface energy variations. Therefore, this paper classifies seasonal patterns of SUHII based on ATCS (annual temperature cycle with seasonal adjustment) into five typical patterns, and further investigates impacts from surface energy variations. There are three major findings. (1) Approximately 70% of global cities are identified as the spring-summer and summer-autumn patterns at daytime, while global cities identified as the winter-spring and insignificant patterns account for 36% and 24%. The seasonal patterns of DNC are significantly affected by that of daytime. (2) The seasonal patterns of SUHII indicate opposite seasonal variations to ∆ EVI (enhanced vegetation index) at daytime and ∆ WSA (white sky albedo) at nighttime. (3) The cities identified as the spring-summer and summer-autumn patterns of SUHII are corresponded to the opposite patterns of latent heat flux at daytime, but similar patterns of net shortwave radiation at both day and night. [ABSTRACT FROM AUTHOR]

• Low carbon building materials alone do not reduce building carbon footprint. • Housing typologies are a critical driver of carbon footprint of building materials. • Low-rise housing operational carbon emissions decline with roof insulation by a factor of 4 to 5. • Each additional storey results in approximately 10–12 % increase in greenhouse gas emissions across housing typologies in Ghana and Senegal. Across West African built environments, patterns of high greenhouse gas emissions are driven by the widespread importation of high embodied carbon building materials by a largely self-built industry and recurring operational carbon costs driven by increased access to fossil-fuel based energy services. Using a whole life cycle assessment (LCA) of major residential typologies in two case-study West African countries, Ghana and Senegal, this paper compares the greenhouse gas emissions of imported building materials with local alternative biogenic and geogenic materials within conventional housing typologies. Results indicated that locally sourced biogenic and geogenic materials may be rendered ineffective in buildings if future typologies do not address the effective space density, passive design strategies and increased renewable energy-use. For the building typology with the highest carbon footprint, the Ghanaian detached house, the substitution of conventional building materials with non-fired earth masonry did not have any significant impact. As shown in the housing typology with the lowest operational to embodied carbon ratio, the Senegalese vertical housing case study, optimizing the thermal mass design of earthen building envelopes can significantly drive down lifetime operational carbon emissions. For tropical low-rise building typologies dominated by high roof area to building volume ratios, roof insulation could drive down operational carbon of the building by a factor of 4 to 5. Although each additional storey results in approximately 10–12 % increase in greenhouse gas emissions, the vertical expansion of housing represents an important driver in reducing greenhouse gas emissions per capita. [ABSTRACT FROM AUTHOR]

• Buildings potential for climate change mitigation is high. • Mitigation actions in the buildings sector can have significant social and economic values. • These enable the achievement of 4 SDGs, reinforce 7 other. • And are linked to the achievement of 5 SDGs (SDG3, SDG7, SDG8, SDG11, and SDG13). • Trade-offs were identified for 9 SDGs. Buildings are responsible for a big part of total GHG emissions; therefore, their climate change mitigation potential is high. But research shows that mitigation actions in the sector can have significant social and economic values beyond reduction of energy consumption and the associated GHG emissions. This paper summarizes these multiple impacts of mitigation actions in buildings, which are related to microeconomic and macroeconomic effects, health impacts, environmental benefits, better management of natural resources, impacts on social well-being, and energy security implications, and assesses their interactions (synergies and trade-offs) with the UN SDGs. The findings of our analysis show that climate change mitigation actions in buildings enable the achievement of 4 SDGs, reinforce 7 others, and are inextricably linked to the achievement of 5 SDGs, namely SDG3: good health and well-being, SDG7: affordable and clean energy, SDG8: decent work and economic growth, SDG11: sustainable cities and communities, and SDG13: climate action. On the other hand, trade-offs were identified for 9 SDGs, with rather minor implications, which can be further eliminated with the implementation of appropriate policies. [ABSTRACT FROM AUTHOR]

• Using the ADOPT algorithm as a conflict resolution model for urban flood management. • Grouping agents as active and passive considering their investment on flood control. • Developing some quadratic functions for simulating active agents' utilities. • Using SWMM to simulate urban flood quantity and the average flood depth. • Using stakeholder analysis and ADOPT reduces the average flood depth by 58 %. The management of water resources in urban environments is challenging due to the existence of numerous stakeholders and the large number of affected people. In this paper, agents in an urban environment are categorized as active, passive, and monitoring agents, and a new mechanism is proposed to determine the flood control motivation functions (FCMFs) of active agents. An FCMF shows the motivation of an agent for investing and participating in a flood control activity. Also, for the first time, the effectiveness of a conflict resolution model based on asynchronous distributed constraint optimization (ADOPT) is evaluated for urban flood management. To evaluate the effectiveness of the proposed framework, it is applied to the eastern drainage catchment of Tehran, the capital city of Iran. The FCMFs of active stakeholders are modeled using some mathematical functions. To determine the FCMFs of active agents, an economic optimum point is suggested. This point is determined based on the construction costs of flood control infrastructures and flood damage costs. The utility functions of passive agents are modeled using a regression analysis. Flood management scenarios include a combination of water transfer canals, pipes, and ponds with real-time operating methods. ADOPT is used for solving Distributed Constraint Optimization Problems (DCOPs). The goal in DCOPs is to assign values to these variables in an approach that maximizes a global objective function while satisfying the constraints of each agent. The results show that by using the ADOPT-based conflict resolution model, the average depth of flooding is reduced from 24 cm to about 10 cm, and this is associated with the satisfaction of more than 90 percent of stakeholders. A decline in Average Flood Depth (AFD) has been observed with increased usage of technological methods such as constructing ponds or transferring water outside the basin. However, stakeholder desirability is critical and both technical and stakeholder interests should be taken into account to ensure project viability. [ABSTRACT FROM AUTHOR]

• Communication-free protection of MGs/SGs, using non-standard relay characteristics. • Considering N-1 contingency configurations and different operation modes. • Facilitating coordination constraints satisfaction and speed up the protection system. • Linearizing and solving the proposed COP using GA-PSO-LP and WCA-MFO-LP algorithm. • Around a 36 % improvement in the speed of the proposed scheme compared to the available ones. Smart grids (SGs), meshed active distribution networks (ADNs), and microgrids (MGs) frequently experience reconfigurations and changes in their operation modes (grid-connected and islanded), which leads to protection miscoordination and speed challenges. Several research works have studied the protection of MGs/SGs, considering different configurations. On the other hand, non-standard relay characteristics provide some flexibility in protection design. However, the literature review shows that less attention has been paid to the optimal protection of MGs/SGs, incorporating non-standard relay curves and consideration of N-1 contingency configurations and operation modes. This paper aims to respond to this research gap. Also, the slow tripping of backup relays, a common drawback of recent works, is concerned with a modified objective function (OF). The presented coordination optimization problem (COP) is formulated in a mixed-integer nonlinear programming-linear programming (MINLP-LP) form and solved using hybrid heuristic-linear programming algorithms: Genetic algorithm-particle swarm optimization-linear programming (GA-PSO-LP) and water cycle algorithm-moth flame optimization-linear programming (WCA-MFO-LP). The introduced research is applied to the distribution portion of the IEEE-14 test system. The analysis and discussions emphasize that the proposed protection scheme speed is improved by over 36 % compared to available ones. Also, there is no coordination violation under different system configurations. [ABSTRACT FROM AUTHOR]

• In 2013-2021, rising count of shrinking Chinese cities due to uneven regional growth. • China's carbon emissions slowed, more cities with negative or reduced growth. • Shrinking cities often show discord between urban development and carbon emissions. • China's four major urban agglomerations displayed varied developmental traits. Chinese cities face challenges of uneven development, high carbon emission intensity, and low efficiency in urbanization processes. Achieving harmonization and equilibrium between urban development and carbon emissions is crucial for sustainable development. This paper analyzes the development trajectory from 2013 to 2021 of four urban agglomerations in China: Northeast China (NEC), Beijing-Tianjin-Hebei (BTH), Yangtze River Delta (YRD), and Pearl River Delta (PRD). It identifies and calculates the urban spatial development patterns and carbon emissions, comparing the spatial-temporal variations in carbon emissions under different urban development patterns. The study also explores the coupling coordination relationship between these two aspects at various stages. The findings suggest that urban spatial development and carbon emissions are often uncoordinated in shrinking cities. In terms of coordination within urban agglomerations, BTH and NEC show suboptimal development, characterized by overall lag and polarization; YRD exhibits the best development, being consistently stable and balanced; PRD is generally improving, though with some cities lagging. Planning departments should revise urban and environmental policies to optimize spatial structures and infrastructure, aligning with regional development and promoting synergy in urban agglomerations. This research provides theoretical and empirical support for China to formulate relevant policies aimed at green, coordinated, and sustainable urban development. [ABSTRACT FROM AUTHOR]

Urban energy consumption is a critical aspect of sustainable urban development, with technological innovations playing a pivotal role in shaping energy usage patterns. This paper presents a comprehensive analysis of urban energy consumption dynamics in relation to the adoption of technology across various sectors, including transportation, residential, industrial, and commercial domains. Through extensive data collection and advanced statistical analyses, we investigate the correlation between technology adoption rates and energy consumption behaviors in urban areas. Our findings reveal a strong positive correlation between technology adoption rates and reduced energy consumption across sectors. We employ spatial analyses to identify localized successes, shedding light on regions where technology-driven initiatives have significantly lowered energy demands. These insights offer valuable guidance for urban planners and policymakers aiming to implement targeted interventions and replicate effective strategies. Furthermore, the paper emphasizes the transformative potential of innovative solutions, ranging from smart infrastructure to industrial automation, in promoting energy efficiency and environmental sustainability. By fostering the integration of such technologies, cities can mitigate their carbon footprint, enhance energy resilience, and create more livable environments for residents. This research contributes to the discourse on urban energy transitions and provides actionable insights for urban policymakers and stakeholders striving for a greener, more sustainable urban future. • Urban energy study integrates tech for sustainable transitions. • Optimized urban planning with technology-driven energy solutions. • Innovative model promotes green, resilient cities through tech adoption. [ABSTRACT FROM AUTHOR]

• Simulate and analyze the characteristics of LULC changes from 2000 to 2030. • UTFVI is used to describe the thermal environment of the PRD urban agglomeration. • Machine learning algorithms are applied to predict the seasonal LST, UTFVI, and UHI. • Explore the response between urban land expansion and the thermal environment. Land use practices in urban areas exert a profound influence on the urban thermal environment and the pursuit of sustainable development. This paper aims to investigate and forecast future changes in land use/land cover (LULC) and their response to seasonal variations in land surface temperatures (LST), the urban thermal field variance index (UTFVI), and the urban heat island effect (UHI). The artificial neural network based on cellular automata (ANN-CA) and the improved whale optimization based on long short-term memory (WOA-LSTM) algorithms are used to predict the LULC, UTFVI, and UHI characteristics in the Pearl River Delta (PRD) urban agglomeration. The results show that urban land will likely expand from 4335 km2 to 8292 km2 from 2000 to 2030. The LST continues to increase, and the maximum temperature in summer will likely increase to 44.6 °C in 2030. Without the intervention of effective cooling measures, the area with LST≥35 °C will likely increase to 4873 km2, and the proportion of areas with LST≥20 °C will likely reach 63.72 % in the winter of 2030. The strongest level of UTFVI expansion is significant in summer, and the area is likely to increase by 83.64 % in 2030. Urban land has the highest percentage in the high temperature region relative to other land use categories. Similar to the trend of LST changes, UHI is expected to notably increase by 2030, with minimum and maximum UHI values projected to rise. This study may provide new perspectives on thermal environment management and sustainable urban development. [ABSTRACT FROM AUTHOR]

The rapid increase in Electric Vehicle (EV) adoption leads to significant challenges for charging station operators due to the unbalance between the growing demand for charging services and their limited power capacity connected to the grid. To tackle the challenge, this paper applies a two-step architecture in which an energy management system (EMS) in the first step determines the available capacity to charge the present fleet of EVs, after which in the second step this capacity is distributed over the individual EVs. To optimally allocate available power and satisfy user requirements, a user priority-based charging management strategy is proposed. Such priority can optimally order the set of EVs to be charged based on user input. However, relying solely on user-estimated input can be prone to incorrect priority due to inaccurate estimations. Therefore, we introduced a clustering of charging sessions based on the user-provided estimated information in the proposed priority function. These clusters relax the effect of inaccurately estimated user input by grouping charging sessions with similar behavior. Our proposed priority can increase user satisfaction by up to 30%, as measured by the percentage of requested energy that is delivered to users, compared to scenarios without priority, 10% more than priority based solely on estimation information, and 8% more than first-come-first-serve. To avoid exposing the personal behavior of the user, we introduce a decentralized approach, applying a consensus-based method that allows local control per EV charging station and only requires minimal communication of a consensus variable with neighboring charging stations. By introducing the priority in the communication weight matrix of the consensus-based algorithm, we accelerate the convergence rate more than 10 times. Simulation results based on real-world data sets in Belgium demonstrate the proposed method scales well with growing fleet sizes. • A privacy-friendly, decentralized, two-stage architecture for prioritized EV charging. • New priority function based on clustering charging sessions and user preferences. • Prioritizing EV charging for users can increase satisfaction by 30%. • The consensus-based method with priority achieves a 10-fold faster convergence. • Real-world charging session data in Belgium was used. [ABSTRACT FROM AUTHOR]

• Introducing a two-stage multi-layer method to organize energy and balancing markets. • Designing an MPEC to model profit-seeking aggregators engaged with smart end-users. • Presenting a robust technique for handling intra-hour balancing requirements of ADN. • Increasing social welfare and decreasing the clearing price using online switching. The increasing integration of Renewable Energy Sources (RESs) and the replacement of fossil fuel vehicles with electric types in distribution systems, while enhancing economic and environmental aspects, have introduced new challenges to network production-consumption balance due to the inherent randomness of these resources. This factor has magnified the significance of balancing markets in renewable-based distribution networks, as these markets address uncertainties and are vital for operational stability. Consequently, this paper introduces a two-stage multi-layer methodology for organizing local energy and balancing markets among Residential Microgrids (RMGs) within an Active Distribution Network (ADN). The AND operator organizes both energy and balancing markets. In the first stage, the intra-day energy market operates, engaging non-profit-seeking aggregators, RMGs, and ADN. Moving to the second stage, the intra-hour balancing market is conducted involving profit-seeking Flexible Load (FL) and Electric Vehicle (EV) aggregators, RMGs, and ADN. The ADN operator organizes both markets and can alter the network topology online within the energy market. The planning of profit-seeking aggregators is formulated using Karush-Kuhn-Tucker (KKT) conditions and Strong Duality Theory (SDT) in the form of Mathematical Programming with Equilibrium Constraints (MPEC), considering the correlation of aggregators' profit with the satisfaction index of end-users. The simulation results of the proposed methodology on a modified 118-bus IEEE distribution test system using GAMS indicate that this approach not only provides a significant share of balancing capacities through FLs and EVs but also ensures system stability against intra-hour fluctuations across various scenarios. The results also validate that the proposed methodology achieves a reduction of 24.8 % in power losses and 5.06 % in market costs, while simultaneously ensuring profitability for both aggregators and RMGs. [ABSTRACT FROM AUTHOR]

In the realm of network intrusion detection using machine learning, feature selection aims for computational efficiency, enhanced performance, and model interpretability, preventing overfitting and optimizing data visualization. This paper proposes a filtering method for feature selection, which optimizes information quantity and linear correlation between resultant features. The method identifies Pareto dominant pairs of informative and correlated features, constructs a graph, and selects key features based on betweenness centrality in its connected components. The proposal yields a more concise and informative dataset representation. Experimental results, using three diverse datasets, demonstrate that the proposal achieves more than 95% accuracy in classifying network attacks with just 14% of the total number features in original datasets. [ABSTRACT FROM AUTHOR]

Existing RFID localization techniques mainly focus on the location of a single target, which do not fully utilize the multi-targets identification merit of UHF RFID systems. In this paper, a multi-targets localization algorithm called merged re-shaken particle swarm optimization (MRPSO) is proposed. The ranging information and the angle information, which are obtained by using multi-frequency phase information with the help of frequency hopping technique, are merged together during the iteration process of MRPSO. In addition, based on the traditional PSO algorithm, a low weight particle filtering method was proposed, and a re-shaken scheme was introduced to improve localization accuracy. By allocating particles to each target, MRPSO can obtain each target location simultaneously after PSO process, which avoids time consuming. The experimental results show that MRPSO can achieve single-station multi-target localization with a median accuracy of 9.64 cm. [ABSTRACT FROM AUTHOR]

In scenarios where traditional ground base stations (BS) are unavailable, Unmanned Aerial Vehicles (UAVs) serve as aerial BS for enabling Internet of Things (IoT) communications. This paper introduces a UAV-based downlink communication model, specifically designed to address the challenge of UAVs' limited energy resources. Our approach innovatively employs simultaneous wireless information and power transfer (SWIPT) technology, enabling the UAV to concurrently transmit information and energy to IoT devices, a crucial capability in remote or emergency areas. The core of our contribution lies in the meticulous optimization of the UAV trajectory, power splitting (PS) ratio, and communication scheduling. These optimizations are vital for maximizing energy efficiency (EE), thereby reducing the energy consumption of the UAV while ensuring high-quality communication services. The dual objectives of amplifying EE and curtailing flight time are integrated into our model, conventional solution methods fall short in addressing this non-convex optimization problem, compounded by the complexities of UAV trajectory, PS ratio, and scheduling constraints. To overcome these challenges, we reformulate the problem as a Markov Decision Process (MDP). We then leverage the powerful reward maximization capabilities of deep reinforcement learning (DRL) to enable the UAV to take optimal, energy-efficient actions in each time slot. Our simulation results are promising, indicating that the DRL algorithm effectively optimizes the UAV trajectory and significantly enhances EE. The outcomes of our research reveal a marked improvement in UAV EE along the optimized trajectory, outperforming several alternative trajectories. Furthermore, we demonstrate that a dynamic PS ratio is more effective than a fixed ratio, highlighting the superiority of our approach. This synergy of trajectory optimization and adaptive PS ratio adjustment represents a significant advancement in efficient, sustainable UAV-enabled IoT communication, particularly under challenging conditions where conventional communication infrastructures are lacking. [ABSTRACT FROM AUTHOR]

Predicting agricultural commodity prices accurately is of utmost importance due to various factors such as perishability, seasonality, production uncertainty etc. Moreover, the substantial volatility that may be exhibited in time series further adds to the complexity and constitutes a significant challenge. In this paper, a Hidden Markov (HM) guided Deep Learning (DL) models has been developed on nonlinear and nonstationary price data of agricultural commodities for forecasting by considering technical indicators viz., Moving Average (MA), Bollinger Bands (BB), Moving Average Convergence Divergence (MACD), Exponential MA (EMA) and Fast Fourier Transformation (FFT). HM Models (HMMs) can effectively handle the sequential dependencies and hidden states, while DL approach can learn complex patterns and relationships within the price series and thus the drawback of lack of generalization capability in the DL model has been overcome by HMM. In this study, the Potato price data of the Champadanga district of West Bengal, India has been utilized to assess the performance of the proposed technique. HMM has been combined with six baseline DL models viz., Recurrent Neural Networks (RNN), Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), Bidirectional LSTM (BiLSTM) and Bidirectional GRU (BiGRU) for forecast modeling. Performance evaluation metrics viz., Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE) and the insightful Diebold–Mariano (DM) test revealed that Hidden Markov hybridized with DL models surpassed baseline DL models in forecasting accuracy for 1-week, 4-week, 8-week and 12-week ahead DL predictions. The proposed approach holds significant promise for enhancing the precision of agricultural commodity price forecasting with far-reaching implications for various stakeholders such as farmers and planners. • A novel Hidden Markov based Deep Learning (DL) models for accurate agricultural commodity price forecasting. • Addresses DL model generalization challenges by integrating sequential dependencies and hidden states obtained from HMMs. • Proposed models outperform baseline models - RNN, CNN, LSTM, GRU, BiLSTM, and BiGRU for price predictions of agriculture commodities. • Evaluated using RMSE, MAPE, MAE and Diebold Mariano test, for accuracy and reliability of the proposed approach. • Offers precision in commodity price forecasts, benefiting stakeholders such as farmers, planners and policymakers. [ABSTRACT FROM AUTHOR]

Co-training was originally designed for multi-view data. Subsequent theoretical research has extended co-training to the application of single-view data. The construction of a feature subspace is one of the methods to expand single-view data into multi-view data, so the establishment of a feature subspace is the key to this approach. In this paper, the kernel method is used to form an implicit feature subspace, to perform multi-view co-training on single-view data. Because the attribute value in the feature subspace is not known, the subspace is a pseudo-view. To make the view adapt to the base classifier, this paper uses the neighborhood classifier as the base classifier and proposes an adaptive kernel function and three kernel parameter optimization methods according to the characteristics of the neighborhood classifier to build the feature subspace adapted to the neighborhood classifier. The decision of the neighborhood classifier needs to be made based on information granules generated by unlabeled objects. In the iteration of the feature subspace, we can continuously learn and optimize the information granule, and finally form what we expect, to get the implicit feature space corresponding to the granule and improve the accuracy of the base classifier. Finally, taking five data sets from UCI, and using accuracy and F1-score as evaluation indicators, we conduct a comparative experiment. The experimental results show that an adaptive kernel function, three kernel parameter optimization methods, and the co-training method presented in this paper are effective. • Three-way decision based on income-cost sensitivity. • Adaptive kernel function for neighborhood information granule. • Kernel parameter optimization methods for neighborhood information granule. • Multi-pseudo-view granular structure co-training based on kernel method. [ABSTRACT FROM AUTHOR]

Wind Energy is rapidly growing into one of the most popular energy options for power generation. However, the unpredictability of wind necessitates the employment of a distribution function when describing the wind environment. In the depiction of wind speeds, the two significant parameters of the Weibull distribution, such as the scale parameter and the shape parameter are often utilized. Therefore, it is essential to choose the most appropriate approach for estimating these parameters. Furthermore, the uncertainty in delegated power from variable wind speeds makes system management challenging. In this paper, the Weibull distribution parameters were determined using the Pelican Optimization Algorithm (POA). POA has gained extensive popularity among the research community and is currently used to address a wide range of optimization problems. However, the exploration and exploitation are not properly balanced in this algorithm. To overcome this problem a novel hybrid algorithm namely Mutualism phase based POA (MPOA) is proposed with the help of mutualism phase of Symbiotic Organisms Search (SOS) algorithm. To demonstrate the efficacy and robustness MPOA is applied on multi-objective Optimal Power Flow (MO-OPF) problems. For this study IEEE 30 bus standard system and modified IEEE 30 bus system consisting of two wind farms are taken. The purpose of this work is to examine the impact of changing the Weibull parameters, reverse and penalty cost coefficients on the overall generation cost while considering all the security aspects. ● The efficiency and robustness of Pelican Optimization Algorithm (POA) is investigated for single objective and multi-objective Optimal Power Flow (OPF) as well as Stochastic Optimal Power Flow (SOPF) problems. ● A novel hybrid Algorithm namely Mutualism phase based Pelican Optimization Algorithm (MPOA) is developed. ● Results shows the superiority of MPOA over POA. ● MPOA and POA are implemented in IEEE 30 bus test system and modified IEEE 30 bus system contains two wind generator having capacity of 80 MW and 50 MW respectively. [ABSTRACT FROM AUTHOR]

In the domain of automated test case generation for path coverage (ATCG-PC), commonly used evolutionary optimization algorithms face significant computational overhead due to the necessity of executing the test program for individual fitness evaluations. To address this challenge and enhance efficiency while ensuring comprehensive coverage, this paper proposes a Hierarchical Surrogate-Assisted Differential Evolution (HSADE) approach. HSADE innovatively incorporates two surrogate models: a Global Surrogate Model (GSM) utilizing Gaussian Process Regression (GPR) for a macroscopic view of the fitness landscape, and a Local Surrogate Model (LSM) employing Radial Basis Function Network (RBFN) for precise fitness estimations in targeted subspaces. This hierarchical approach facilitates a two-phase optimization process: an initial coarse search to pinpoint areas of interest followed by a focused, fine-grained search for precision, where LSM is combined with differential evolution (DE) algorithm for fine optimization in these regions. To mitigate the risk of converging to local optima, HSADE employs Random Opposition-Based Learning (ROBL) to enhance the population diversity, leveraging the uncertainty assessment capabilities of the GPR. Our experimental validation, conducted on a diverse set of benchmark programs, demonstrates HSADE's effectiveness in reducing the number of fitness evaluations and computational time required for generating high-quality test cases. Compared to established evolutionary algorithms, HSADE achieves superior path coverage with significantly less computational effort. • An ATCG-PC method based on DE and Hierarchical surrogate model (HSM) is proposed. • We proposed HSM for reduced fitness costs and coarse-to-fine optimization. • We evaluated our method's effectiveness across various benchmark programs. • Adopted modified DE and random perturbations for faster convergence and diversity. • Our method is found to be efficient in generating test cases for path coverage. [ABSTRACT FROM AUTHOR]

In wireless sensor networks (WSN), we often detect the monitoring areas among different sensors so that the sensors can be switched on and off adaptively to save energy and extend their lifetime. Inspired by the principle of WSN, a WSN-based adaptive differential evolution (WSNADE) algorithm is proposed in this paper, together with a WSN-based adaptive niching technique (WANT) and two novel strategies called protection-based dual-scale mutation (PDM) strategy and multi-level reset (MLR) strategy, for solving multimodal optimization problems (MMOPs). In WANT, each individual is considered as a sensor with its monitoring area. If the monitoring areas of two individuals intersect, which means these two individuals monitor the similar area and should be partitioned into the same niche. In this way, WANT can adaptively form a niche for each individual, avoiding the sensitivity of niching parameters. Based on WANT, the PDM strategy is designed to select the appropriate mutation strategy for each individual. Besides, to save fitness evaluations (FEs) for exploring more promising areas, the MLR strategy is developed to store the promising individuals and reset the stagnant individuals. The experimental results on 20 multimodal benchmark test functions in CEC2015 multimodal competition show that the proposed WSNADE algorithm generally performs better than or at least comparable with other state-of-the-art multimodal algorithms, including the winner of the CEC2015 competition. Finally, WSNADE is applied to a real-world multimodal application in multiple competitive facilities location design (MCFLD) problem to illustrate its practical applicability. • Design a WSN-based adaptive niching technique (WANT) to form niches adaptively. • Propose a protection-based dual-scale mutation (PDM) strategy. • Design a multi-level reset (MLR) strategy to save and reset individuals. • Illustrate the algorithm advantages in MMOPs and multimodal application. [ABSTRACT FROM AUTHOR]

The decision-maker's judgment deviates from uncertain attribute information will lead to decision risk in multiple attribute decision making (MADM), and different aggregation approaches result in different risk levels. This paper aims to study the risk levels of aggregation operators in MADM with uncertain attribute information. We use the signal detection theory to characterize the decision-maker's noisy perceptions of multiple attributes to present his/her judgment deviation. Then, we establish the aggregation models to aggregate these perceptions based on the weighted averaging (WA) and the ordered weighted averaging (OWA) operators. Furthermore, a risk measurement model of each aggregation approach is constructed to measure the risk levels of the commission risk (CR), the omission risk (OR), and the overall risk. A numerical example is used to verify the validity of the proposed model, while simulation experiments are designed to compare the risk levels of the WA and OWA operators. The results reveal that the overall risk level of the WA operator is higher than that of the OWA operator when judging the quality of the alternative with high standards; otherwise, the WA operator is lower. This finding provides a scientific reference for aggregation approach selection under uncertain information. Permanent link to reproducible Capsule: https://doi.org/10.24433/CO.0911610.v1. • We characterize a decision-maker's noisy perceptions of attributes. • We obtain the noisy perceptions of alternatives according to the characteristics of aggregation approaches. • We propose a risk measurement model of aggregation approaches for MADM. [ABSTRACT FROM AUTHOR]

Due to the escalating electricity demand from industrialization and modernization, it is imperative to explore clean and sustainable energy sources. Solar energy has become a feasible solution for this surging demand. Solar panels, vital components of solar power systems, are crucial in converting sunlight into electricity. However, selecting the most suitable solar panel is a complex task involving subjective and measurable parameters involving uncertainties. To address the uncertainties and ambiguities in real-life problems, the theory of Pythagorean fuzzy sets with distance measures has emerged as a flexible and superior tool. Nevertheless, many existing distance functions often fail to meet necessary metric conditions, leading to inaccurate and unreasonable outcomes. These limitations are pointed out by many literature. In addition, we observe a serious drawback of parameter dependency of some existing measures. This paper proposes a novel metric for Pythagorean fuzzy sets using the matrix norm to overcome these drawbacks. Additionally, we discuss various mathematical properties and provide geometrical representations for the proposed distance measure. To demonstrate the superiority of the proposed measure, we conduct a comparative study against existing distance measures. Furthermore, we develop a Pythagorean fuzzy-method based on the removal effects of criteria-stepwise weight assessment ratio analysis-vlse kriterijumska optimizacija kompromisno resenje (PF-MEREC-SWARA-VIKOR) method for selecting solar panel systems. Our approach incorporates the MEREC method for objective criteria, utilizes the SWARA method to calculate subjective weights, and employs the VIKOR method in the Pythagorean fuzzy context to determine the preference order of alternatives. We conduct sensitivity analysis and comparative studies with existing developed methods to validate our method. Highlight the effectiveness and advantages of our novel approach in selecting solar panels. Finally, exploring the future research directions and challenges associated with the proposed methodology. • Escalating electricity demand necessitates exploring clean and sustainable energy sources. • Solar energy is a feasible solution to meet the surging demand. • A novel metric for Pythagorean fuzzy sets using the matrix norm is proposed to overcome limitations and enhance accuracy. • A Hybrid PF-MEREC-SWARA-VIKOR method optimizes selection for solar panels. • Comparative studies validate superiority of proposed approach in solar panel selection. [ABSTRACT FROM AUTHOR]

During the synthesis of acceleration autopilots for high dynamic flight vehicles (HDFV), autopilots with feedback of angular acceleration (AFAA) have become more perspective with stringent requirements on response speed and high maneuverability, compared with autopilots with feedback of angular rate (AFAR). Integral reinforcement learning (IRL) method has now proved to be an effective technique for adaptive optimal control of partially unknown nonlinear systems. In this paper, a novel data-driven IRL algorithm with "actor–critic" structure is proposed for HDFV utilizing AFAA. As an advanced model-free approach, "actor–critic" based IRL algorithm learns optimal behaviors by observing the real-time responses from the environment under the action of nonoptimal control policies. Instead of solving algebraic Riccati equation directly, the control policy updates online via the solution of proposed IRL Bellman equation with sensed quantities. Numerical simulation is carried out to validate the effectiveness of proposed online IRL-based angular acceleration autopilot for HDFVs. Besides, the tracking performance under different wave commands, the robustness against parameter uncertainties and the noise attenuation capacity between classical optimal tracking approach and proposed IRL method are analyzed for AFAR and AFAA, respectively. Simulation results show that, angular acceleration autopilot with proposed integral RL algorithm possesses better tracking performance against various disturbances. • An angular acceleration feedback HDFV autopilot is proposed for higher performances. • A data–driven integral RL algorithm with "actor–critic" structure is proposed. • Tracking performances of autopilots with different algorithms are analyzed. [ABSTRACT FROM AUTHOR]

Deep Reinforcement Learning (DRL) has achieved considerable success in games involving perfect and imperfect information, such as Go, Texas Hold'em, Stratego, and DouDiZhu. Nevertheless, training a state-of-the-art model for complex imperfect-information card games like DouDiZhu and Big2 remains resource and time-intensive. To address this challenge, this paper introduces two innovative methods: the Opponent Model and Optimized Deep Monte-Carlo (ODMC). These methods are designed to improve the training efficiency of Deep Monte-Carlo (DMC) for imperfect-information card games. The Opponent Model predicts hidden information, enhancing the agent's learning speed in DMC compared to the original training that only utilizes observed information as input features. In ODMC, the Minimum Combination Search (MCS) is a heuristic search algorithm based on dynamic programming. It calculates the minimum combination of actions in the current state, and ODMC uses MCS to filter suboptimal actions in each state. This reduces the action space considered by DMC, resulting in faster training that focuses on evaluating the most promising actions. The effectiveness of the proposed approach is evaluated by examining two complex card games with imperfect information: DouDiZhu and Big2. Ablation experiments are conducted to evaluate both the Opponent Model (D+OM and B+OM) and ODMC (D+ODMC and B+ODMC), along with their combined variants (D+OMODMC and B+OMODMC). Furthermore, D+OMODMC and B+OMODMC are compared with state-of-the-art DouDiZhu and Big2 artificial intelligence (AI) programs, respectively. The experimental results demonstrate that the proposed methods achieve comparable performance to the original DMC, but with only 25.5% of the training time on the same device. These findings are valuable for mitigating both the equipment requirements and training time in complex imperfect-information card games. • Propose a novel Opponent Model and ODMC to improve the learning efficiency of DMC. • Opponent Model predicts hidden information, enhancing learning. • ODMC uses MCS to filter suboptimal actions, speeding up training. • Proposed methods achieve comparable performance with reduced training time. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach to representing the Limit Order Book data at a given timestamp using the Ordered Fuzzy Numbers concept. The limit order book contains all buy and sell orders placed by investors, updated in real-time, for the most liquid securities, even several hundred times a minute. Due to its irregular nature (different and dynamic changes in the number of buy and sell orders), direct calculations on the order book data are not feasible without transforming it into feature vectors. Currently, most studies use a price level-based data representation scheme when applying deep learning models on limit order book data. However, this scheme has limitations, particularly its sensitivity to subtle perturbations that can negatively impact model performance. On the other hand, the ordered fuzzy number is a mathematical object (a pair of two functions) used to process imprecise and uncertain data. Ordered Fuzzy Numbers possess well-defined arithmetic properties. Converting the limit order book data to ordered fuzzy numbers allows the creation of a time series of ordered fuzzy numbers (order books) and use them for further calculations, e.g., to represent input data for deep learning models or employing the concept of fuzzy time series in various domains, such as defining liquidity measures based on limit order book data. In this paper, the proposed approach is tested using one-year market data from the Polish Stock Exchange for the five biggest companies. The DeepLOB model is employed to predict mid-price movement using different input data representations. The proposed representation of Limit Order Book data demonstrated remarkably stable out-of-sample prediction accuracy, even when subjected to data perturbation. • The novel LOB data representation with Ordered Fuzzy Numbers is presented. • The proposed data representation stays mostly the same under data perturbation. • The proposed and commonly used data representations are compared for price predicting. • The proposed data representation keeps model performance stable under data perturbation. [ABSTRACT FROM AUTHOR]

Genetic Programming (GP) can be used to design effective classifiers due to its built-in feature selection and feature construction characteristics. Unbalanced data distributions affect the classification performance of GP classifiers. Some fitness functions have been proposed to solve the class imbalance problem of GP classifiers. However, with the evolution of GP, single-objective GP classifiers evaluated by a single fitness function have poor generalization ability. Moreover, using the best evolved GP classifier for decision-making can easily lead to the possibility of misclassification. In this paper, multi-objective GP is used to optimize multiple fitness functions including AUC approximation (Wmw), Distance (Dist), and Complexity to evolve ensemble classifiers, which jointly determines the class labels of unknown instances. Experiments on sixteen datasets show that our multi-objective GP can significantly improve classification performance compared with single-objective GP, and our proposed ensemble classifiers evolved by multi-objective GP can further improve the classification performance than the single best GP classifier. Comparisons with six GP-based and five traditional machine learning algorithms show that our proposed approaches can achieve significantly better classification performance on most cases. • Proposed multi-objective GP can significantly improve the classification performance compared with single-objective GP. • Proposed ensemble classifiers can further improve the classification performance. • Proposed approaches can achieve better performance than six GP-based and five traditional machine learning algorithms. [ABSTRACT FROM AUTHOR]

Surface defect detection is a crucial inspection phase in ensuring industrial product quality and reliability, particularly in the context of metallic manufacturing components. While existing deep learning-based approaches have demonstrated some effectiveness, the design of certain network structures still lacks consideration for industrial scenarios. This paper proposed a complex metallic surface defect detection neural network which incorporates two innovatively designed modules along with other targeted enhancements. Firstly, the spatial pyramid pooling (SPP) structure is redesigned for richer global-local information fusion. A global feature fusion and redistribution module (GFAR) is designed to fully leverage feature information across different scales. With the combination of a novel global positional attention mechanism (GPAM), GFAR is capable of distinguishing defects from complex backgrounds. Moreover, the asymmetric convolution blocks (ACB) are employed to process the final features, enhancing the representational capacity for intricate defect shapes. Subsequently, the detection head is decoupled in both spatial and task domains to addresses the problems posed by inconsistent focus between classification and regression tasks. Finally, the reassignment of loss functions is undertaken for each respective task to enhance their alignment with the specific requirements of the defect detection task. Extensive ablation experiments are conducted on two steel surface defect datasets, NEU-DET and GC10-DET, to demonstrate the effectiveness of each module. The defects detection accuracy of our method respectively reaches 80.9 % and 84.8 % for the two datasets, which outperforms the majority of state-of-the-art detection neural networks. • A global feature fusion and redistribution (GFAR) module is proposed to strengthen cross-scale feature interactions. • A global positional attention mechanism (GPAM) is integrated into the GFAR to suppress background regions. • A dual context decoupled (DCD) head was constructed to achieve spatial disentanglement for different tasks. [ABSTRACT FROM AUTHOR]

Segmenting plantar pressure images intelligently can provide valuable insight for people with high blood pressure, making bespoke footwear requirements possible and resulting in more comfortable shoe designs. It is, however, difficult to extract design elements from a segmented image dataset. To address this challenge, we propose an ML-GNN model that segments plantar pressure images using metal-earning. The first part of the paper presents a method for extracting image features that reduce the complexity of the ML-GNN algorithm. To create the network structure, we propose optimization meta-based learning. Using a meta-learning-based graphic neural network, we enhance our mask-based CNN prediction model with VGG16 and CNN layers. We pre-processed the plantar pressure dataset using pressure-sensing data acquisition and compared the results. By defining standard image segmentation indices, we demonstrate the high effectiveness of our research. We have developed an ML-GNN model that improves the segmentation accuracy of plantar pressure images and can also be applied to other sensor image datasets. Through our shoe-last customization approach, we enable the shoe industry to manufacture shoes more efficiently, particularly for people with specific healthcare needs who require bespoke shoe designs. Our findings demonstrate the potential of intelligent image segmentation to advance the field of footwear design and improve the lives of people with specific health requirements. • Proposed a meta-learning based graphic convolutional neural networks for segmentation. • Developed the graphic neural networks for image feature extraction. • Optimized the Meta-Based Learning for semantic segmentation • Compared to most current deep neural network to show the effectiveness. [ABSTRACT FROM AUTHOR]

Landslides pose significant risks as natural disasters, highlighting the importance of accurate mapping using remote sensing images for various practical applications. However, due to the challenges arising from incomplete and inaccurate boundary information of foreground landslide polygons, existing methods can only achieve suboptimal performance. To this premise, in this paper, we propose a segmentation network called GMNet that leverages global information extraction and multi-scale feature fusion to enhance the discrimination of landslides from other objects. Specifically, by employing a multi-branch mechanism, our method effectively captures global information, while an improved multi-scale feature fusion technique addresses the issue of varying scales in landslide polygons. Furthermore, semantic enhancement enhances the semantic information of low-level features, bridging the semantic gap and enhancing fusion efficacy. Experimental results demonstrate the effectiveness of our network in segmenting landslide areas accurately within the remote sensing image dataset. Especially, our F1_scores on three benchmarks outperform existing runner-ups by notable margins of 4.81%, 1.72%, and 1.16%, showcasing the value of our method in this domain. • Our method helps to better distinguish landslides from other confusing objects. • Our method effectively addresses the issue of varying resolutions. • Our method improves the fusion effect of different levels of features. • Our method exhibits competitive performance on a landslide segmentation dataset. [ABSTRACT FROM AUTHOR]

Elevator systems in buildings face challenges due to unpredictable passenger flow, which can make scheduling elevators complicated to optimize their operation. Most of the existing algorithms are developed based on pattern recognition and may not be effective in scenarios where patterns are difficult to classify, especially when elevator operations involve uncertain human behaviors. To address this issue, this paper proposes a time-dependent optimization model that considers long-term and multi-floor peaks, with a focus on peak floors. The proposed model accounts for dynamic scheduling patterns of elevators and represents passenger flow direction as a relation matrix. The proposed direction optimization method contains several functions to guide iteration direction and improve the efficiency of an iteration process based on classical algorithms. This method also ensures the stability of Markov chains by adjusting an iteration process. The feasibility of the proposed method is supported by the relevant theory, and experimental results show that the direction-optimized algorithms outperform classical algorithms, resulting in the superb operating efficiency of elevators at a lower cost. This paper contributes to the development of efficient algorithms for scheduling elevators in complex traffic patterns, which can improve performance of elevator group systems in buildings. The proposed method is not only limited to elevators but can also be extended to other transportation systems with flow requirements. • Estimating the relation between peak floors without pattern recognition. • Four relations are defined to classify the passenger flow. • Dynamically modifying three metaheuristic algorithms' iteration law. • The application for transportation systems with unpredictable flow. [ABSTRACT FROM AUTHOR]

Multi-view clustering has achieved many applications in recent years. But the existing multi-view clustering methods face two problems, firstly, the traditional multi-view clustering uses a hard clustering method, which cannot describe the uncertainty between the samples and the clusters, and secondly how to perform effective incremental learning on multi-view data when the number of views increases. Therefore to address the above two problems, we firstly propose a three-way fuzzy spectral clustering algorithm based on fuzzy clustering, which can perform three-way clustering on multi-views and get soft clustering results, thus describing the uncertainty between samples and clusters. Then based on the sequential decision making approach, an incremental learning mechanism is designed for multi-view clustering when the number of views increases. Finally, these two works are combined to propose a multi-view clustering algorithm based on sequential three-way decision making. The experimental results demonstrate that the method proposed in this paper has better clustering accuracy and efficiency compared to the traditional multi-view clustering algorithm. • As incremental data comes in, the performance of the strategy goes up. • Methods can delay decisions when there is insufficient data for multiple views. • Methods are suitable for saving the results obtained by strategies when there is not enough information. • Strategies can be more time efficient than traditional methods. [ABSTRACT FROM AUTHOR]

This paper addresses the critical task of hacker identification within the cyber traceability system. While the latest hacker group identification method based on the heterogeneous graph attention network (HGHAN) holds promise in discovering hacker groups, its potential is hindered by the underutilization of node information and poor training efficiency. Particularly, attribute information dilution during node feature extraction and lengthy training for node embedding vector reassignment when new nodes are added have been observed. To rectify these shortcomings, the paper presents an improved model for hacker group identification. This novel approach leverages dynamic heterogeneous graph node updating to significantly boost efficiency without compromising the original model's classification accuracy. The key aspects of the method involve pre-learning for node attribute training vectors, LSTM (Long Short-Term Memory) and attention mechanisms for node feature vector refinement, and introducing a sparse matrix and dynamic node update scheme. The experimental results demonstrate marked improvements in training efficiency and graph update processes while maintaining classification accuracy. This advancement signifies the improved HGHAN model's capacity to adeptly navigate real-world network dynamics, assisting researchers in pinpointing malicious attackers amid cyber incidents. [Display omitted] • Implement heterogeneous graph node embedding vector updates in dynamic scenarios to replace retraining. • Adopt pre-training in the node feature extraction process to enhance feature utilization. • Introduce a triplet sparse matrix in the node embedding process to save space and improve efficiency. • The experiments show that the proposed model can greatly reduce the time consumption without affecting the identification effect of the basic model. [ABSTRACT FROM AUTHOR]

• This study uses descriptive statistical features and five classifiers—DT, LDA, NB, SVM, and KNN—to recognise hand gestures. • Five classifiers were tested in two situations by dividing the dataset into 80%-20% and 50%-50% training and testing ratios. • The SVM classifies 8 hand gestures with the maximum accuracy at %97.1 for 80%-20% and %96.1 for 50%-50%. • Using seven performance metrics, the five classifiers showed strength and precision with good numerical values. • Our research outperformed nine previous studies using the same MMG signal, demonstrating superior classification accuracy. One of the most significant tools for Human–Computer Interaction (HCI) is body language, namely gestures. Therefore, Gesture recognition using Mechanomyography (MMG) for controlling prostheses and rehabilitation devices has been researched for years. The MMG is gauged as the mechanical vibrations engendered by the muscle in its activation. Hence, MMG data provides information regarding the mechanical activity of muscles. It is obtained from the limb and facilitates the comprehension of hand gestures. A MMG dataset named "MMG DATA" that has already been produced is utilized in this paper. To improve the accuracy of classification and the speed of processing, we have extracted the twelve descriptive statistical features of the eight game motions and their iterations contained in the "MMG DATA" for each subject. Five distinct machine learning algorithms—including Decision Tree (DT), Linear Discriminant Analysis (LDA), Naive Bayes (NB), Support Vector Machine (SVM), and k-Nearest Neighbor (k-NN)—were used to categorize the hand gestures, with the results compared using several performance metrics. Several experiments have been carried out in order to validate the presented models. Additionally, two scenarios have been achieved by splitting the dataset into two different and far apart ratios: the first by randomly partitioning the dataset into 80% for training the models and 20% for testing them, while the second by evenly dividing the dataset into 50% for both training and testing phases. Drawing on the results of the performance metrics, it can be argued that this study effectively distinguishes and classifies the eight hand motions. Furthermore, it is worth noting that the results exhibit significant strength and stability, particularly when transitioning from the initial scenario to the subsequent scenario across all proposed models. Out of the classifiers that were chosen, the SVM emerged as the most successful, achieving a classification accuracy of 97.1%. [ABSTRACT FROM AUTHOR]