Crowdsourcing geographic information for terrorism-related disaster awareness and mitigation: perspectives and challenges DOI Creative Commons
Michaelmary Chukwu, Xiao Huang, Siqin Wang

и другие.

Geo-spatial Information Science, Год журнала: 2025, Номер unknown, С. 1 - 18

Опубликована: Янв. 17, 2025

This systematic review explores the utilization of crowdsourcing for geoinformation in enhancing awareness and mitigating terrorism-related disasters. Out 519 studies identified database search, 108 were deemed eligible analysis. We focused on articles employing various forms platforms, such as Twitter (now known X), Facebook, Telegram, across three distinct phases disasters: monitoring detection, onset, post-incident Notably, we placed particular emphasis integration Machine Learning (ML) algorithms studying crowdsourced terrorism to assess current state research propose future directions. The findings revealed that emerged predominant platform information. Despite prevalence natural language processing data mining, majority did not incorporate ML their analyses. preference qualitative methods can be attributed multifaceted nature terrorism, spanning security, governance, politics, religion, law. Our advocacy is increased from domains geography, earth observation, big data. Simultaneously, encourage advancements existing enhance accurate real-time detection planned onset

Язык: Английский

Algorithmic urban planning for smart and sustainable development: Systematic review of the literature DOI Creative Commons

Tim Heinrich Son,

Zack Weedon,

Tan Yiğitcanlar

и другие.

Sustainable Cities and Society, Год журнала: 2023, Номер 94, С. 104562 - 104562

Опубликована: Март 29, 2023

In recent years, artificial intelligence (AI) has been increasingly put into use to address cities' economic, social, environmental, and governance challenges. Thanks its advanced capabilities, AI is set become one of local governments' principal means achieving smart sustainable development. utilisation for urban planning, nonetheless, a relatively understudied area research, particularly in terms the gap between theory practice. This study presents comprehensive review areas planning which technologies are contemplated or applied, it analysed how support could potentially Regarding methodological approach, this systematic literature following PRISMA protocol. The obtained insights include: (a) Early adopters' real-world applications paving way wider government adoption; (b) Achieving adoption involves collaboration partnership key stakeholders; (c) Big data an integral element effective and; (d) Convergence human crucial urbanisation issues adequately achieve These highlight importance making smarter through analytical methods.

Язык: Английский

Процитировано

198

Deep learning: systematic review, models, challenges, and research directions DOI Creative Commons

Tala Talaei Khoei,

Hadjar Ould Slimane,

Naima Kaabouch

и другие.

Neural Computing and Applications, Год журнала: 2023, Номер 35(31), С. 23103 - 23124

Опубликована: Сен. 7, 2023

Abstract The current development in deep learning is witnessing an exponential transition into automation applications. This can provide a promising framework for higher performance and lower complexity. ongoing undergoes several rapid changes, resulting the processing of data by studies, while it may lead to time-consuming costly models. Thus, address these challenges, studies have been conducted investigate techniques; however, they mostly focused on specific approaches, such as supervised learning. In addition, did not comprehensively other techniques, unsupervised reinforcement techniques. Moreover, majority neglect discuss some main methodologies learning, transfer federated online Therefore, motivated limitations existing this study summarizes techniques supervised, unsupervised, reinforcement, hybrid learning-based addition each category, brief description categories their models provided. Some critical topics namely, transfer, federated, models, are explored discussed detail. Finally, challenges future directions outlined wider outlooks researchers.

Язык: Английский

Процитировано

128

Where Is the Peri-Urban? A Systematic Review of Peri-Urban Research and Approaches for Its Identification and Demarcation Worldwide DOI Creative Commons
Mehebub Sahana, Joe Ravetz, Priyank Pravin Patel

и другие.

Remote Sensing, Год журнала: 2023, Номер 15(5), С. 1316 - 1316

Опубликована: Фев. 27, 2023

Metropolitan areas worldwide have grown rapidly and are usually surrounded by peri-urban zones that neither urban nor rural. Despite widespread use of the term ‘peri-urban’, physical determination these spaces is difficult due to their transient nature multiple definitions. While many identified regionally or globally, questions persist on where exactly located, what most apt methods delineate its boundaries. The answers pertinent towards framing targeted policies for governing dynamic socio-spatial transformations in zones. This paper reviews research over last 50-plus years discern existing methodologies identification/demarcation applications. For this, a total 3124 documents studies were through keyword searches Scopus Google Scholar databases. Thereafter, 56 examined explicitly dealt with demarcating Results reveal there no standout/generalized method demarcation. Rather, approaches geographically specific vary across developed developing countries, differences land-use patterns, socioeconomic drivers, political systems. Thus, we recommend ‘pluralistic’ framework determining boundaries at regional–global scale enable better relevant policies.

Язык: Английский

Процитировано

73

Mapping the landscape and roadmap of geospatial artificial intelligence (GeoAI) in quantitative human geography: An extensive systematic review DOI Creative Commons
Siqin Wang, Xiao Huang, Pengyuan Liu

и другие.

International Journal of Applied Earth Observation and Geoinformation, Год журнала: 2024, Номер 128, С. 103734 - 103734

Опубликована: Март 11, 2024

This paper brings a comprehensive systematic review of the application geospatial artificial intelligence (GeoAI) in quantitative human geography studies, including subdomains cultural, economic, political, historical, urban, population, social, health, rural, regional, tourism, behavioural, environmental and transport geography. In this extensive review, we obtain 14,537 papers from Web Science relevant fields select 1516 that identify as studies using GeoAI via scanning conducted by several research groups around world. We outline applications systematically summarising number publications over years, empirical across countries, categories data sources used applications, their modelling tasks different subdomains. find out existing have limited capacity to monitor complex behaviour examine non-linear relationship between its potential drivers—such limits can be overcome models with handle complexity. elaborate on current progress status within each subdomain geography, point issues challenges, well propose directions opportunities for future context sustainable open science, generative AI, quantum revolution.

Язык: Английский

Процитировано

40

Computer vision applications for urban planning: A systematic review of opportunities and constraints DOI Creative Commons

Raveena Marasinghe,

Tan Yiğitcanlar, Severine Mayere

и другие.

Sustainable Cities and Society, Год журнала: 2023, Номер 100, С. 105047 - 105047

Опубликована: Ноя. 8, 2023

Computer vision (CV) technology, a key subset of artificial intelligence, provides powerful tools for extracting valuable insights from visual data, which is crucial component the urban planning process. Despite promising potential CV in planning, its applications this context have not been thoroughly examined. This lack scholarship represents critical knowledge gap our understanding role planning. paper aims to provide consolidated process and challenges planners face during adoption CV. The conducts systematic literature review tackle questions how applied process, what are adopting techniques process? findings revealed: (a) could support broad range tasks including data collection analysis, issue identification prioritisation, public participation, plan design adoption, implementation evaluation; (b) improve decision-making through various information, but limitations need be considered, and; (c) Utilisation efforts sustainable development. study informs policy- plan-making circles by providing into existing prospective contributions transforms augments practices, elaborates adoption.

Язык: Английский

Процитировано

34

The potential of remote sensing and GIS in urban building energy modelling DOI Creative Commons
Arunim Anand, Chirag Deb

Energy and Built Environment, Год журнала: 2023, Номер 5(6), С. 957 - 969

Опубликована: Июль 23, 2023

As the world continues to urbanize at an unprecedented rate, energy demand in cities is rising. Buildings account for over 75% of all consumed and are responsible two-thirds emissions. Assessment buildings a highly integrative endeavour, bringing together interdisciplinary fields urban studies, along with host technical domains namely, geography, engineering, economics, sociology, planning. In last decade, several building modelling tools (UBEMs) have been developed estimation as well prediction cities. These models useful policymaking they can evaluate future scenarios. However, data acquisition generating input database UBEM has major challenge. this review, comprehensive assessment potential remote sensing GIS techniques presented. Firstly, most common variables identified by reviewing recent publications on then studies related corresponding these explored. More than 140 research papers review articles relevant applications level extraction areas investigated purpose. After going through details required each components studying possibility acquiring some those using sensing, it inferred that satellite Unmanned Aerial Vehicles (UAVs) strong enhancing space but their applicability limited. Further, challenges usage technologies possible solutions also presented study. It recommended utilise existing methodologies extracting information from UBEM, newer such machine learning artificial intelligence.

Язык: Английский

Процитировано

32

Prediction of transportation energy demand in Türkiye using stacking ensemble models: Methodology and comparative analysis DOI Creative Commons
Julian Hoxha, Muhammed Yasin Çodur, Enea Mustafaraj

и другие.

Applied Energy, Год журнала: 2023, Номер 350, С. 121765 - 121765

Опубликована: Авг. 25, 2023

The transportation sector accounts for 61.5% of global oil consumption and is responsible 29% the world's total energy demand. Passenger utilizes around 50%–60% used transportation-related activities. Accurate prediction future essential governments to make well-informed decisions regarding infrastructure development utilization, which supports United Nations' Sustainable Development Goals (SDGs) advances shift a net-zero carbon economy. With expected increase in population, vehicles, economic growth, it predict demand ensure sustainable urban transportation. This crucial not only prosperity but also promoting human health mitigating emissions. Therefore, plays vital role designing making informed investment policy decisions. study proposes novel methodology investigates application machine learning stacking ensemble method with hyperparameter tuning multicollinearity removal Turkey based on historic data from 1975–2019. dataset includes GDP, year, vehicle miles traveled, price, passenger ton-miles traveled as features. A performance evaluation comparison 19 algorithms first carried out find best candidate models, including eXtreme Gradient Boosting algorithm. uses all features two them during training phase, takes into consideration 4-fold cross-validation. combination permutation importance hierarchical clustering algorithm Spearman rank-order correlations dimensionality reduction dataset. Extra Tree Regressor ADABoost Regressor, are both placed second level suggested meta-regressors that proposed ensembles because they perform better compared single In total, eight models – four each were developed investigated considering separately. Six metrics R-squared, MSE, MAE, RMSE, RMSLE, MAPE assess models. Trees can be meta-regressor model achieves an R-squared value approximately 0.99 when taken consideration. When considered same achieve accuracy 0.98. These findings have potential contribute more accurate results, can, turn, lead improved strategies managing Additionally, this research support advancement alternative technologies promote development, ultimately helping move towards

Язык: Английский

Процитировано

31

Socio-Spatial Experience in Space Syntax Research: A PRISMA-Compliant Review DOI Creative Commons
Ju Hyun Lee, Michael J. Ostwald, Ling Zhou

и другие.

Buildings, Год журнала: 2023, Номер 13(3), С. 644 - 644

Опубликована: Фев. 28, 2023

Characterising and predicting socio-spatial experience has long been a key research question in space syntax research. Due to the lack of synthesised knowledge about it, this review conducts first systematic scoping on relationships between spatial properties experiential values. Adopting “Preferred Reporting Items for Systematic reviews Meta-Analyses” (PRISMA) framework, identifies 38 studies that examine experiences architectural, medical, urban spaces. The data arising from are used identify trends sub-field research, including growth methods applications analytics since 2016 methodological approaches, characteristics, factors experience. identified using framework employs mixture descriptive, correlation, regression dynamic effects configurations human experiences. Arising results review, article further collective, predictive model consisting five syntactic predictors three categories This article, finally, examines gaps limitations body suggests future directions.

Язык: Английский

Процитировано

26

Remote sensing of diverse urban environments: From the single city to multiple cities DOI Creative Commons
Gang Chen, Yuyu Zhou, James A. Voogt

и другие.

Remote Sensing of Environment, Год журнала: 2024, Номер 305, С. 114108 - 114108

Опубликована: Март 14, 2024

Язык: Английский

Процитировано

18

A comprehensive survey on weed and crop classification using machine learning and deep learning DOI Creative Commons
Faisal Dharma Adhinata, Wahyono Wahyono, Raden Sumiharto

и другие.

Artificial Intelligence in Agriculture, Год журнала: 2024, Номер 13, С. 45 - 63

Опубликована: Июнь 26, 2024

Machine learning and deep are subsets of Artificial Intelligence that have revolutionized object detection classification in images or videos. This technology plays a crucial role facilitating the transition from conventional to precision agriculture, particularly context weed control. Precision which previously relied on manual efforts, has now embraced use smart devices for more efficient detection. However, several challenges associated with detection, including visual similarity between crop, occlusion lighting effects, as well need early-stage Therefore, this study aimed provide comprehensive review application both traditional machine learning, combination two methods, across different crop fields. The results show advantages disadvantages using learning. Generally, produced superior accuracy compared under various conditions. required selection right features achieve high classifying conditions consisting early growth effects. Moreover, precise segmentation stage would be cases occlusion. had advantage achieving real-time processing by producing smaller models than thereby eliminating additional GPUs. development GPU is currently rapid, so researchers often accurate identification.

Язык: Английский

Процитировано

18