Improved Use of Drone Imagery for Malaria Vector Control through Technology-Assisted Digitizing (TAD)

Drones have the potential to revolutionize malaria vector control initiatives through rapid and accurate mapping of potential malarial mosquito larval habitats to help direct field Larval Source Management (LSM) efforts. However, there are no clear recommendations on how these habitats can be extracted from drone imagery in an operational context. This paper compares the results of two mapping approaches: supervised image classification using machine learning and Technology-Assisted Digitising (TAD) mapping that employs a new region growing tool suitable for non-experts. These approaches were applied concurrently to drone imagery acquired at seven sites in Zanzibar, United Republic of Tanzania. Whilst the two approaches were similar in processing time, the TAD approach significantly outperformed the supervised classification approach at all sites (t = 5.1, p < 0.01). Overall accuracy scores (mean overall accuracy 62%) suggest that a supervised classification approach is unsuitable for mapping potential malarial mosquito larval habitats in Zanzibar, whereas the TAD approach offers a simple and accurate (mean overall accuracy 96%) means of mapping these complex features. We recommend that this approach be used alongside targeted ground-based surveying (i.e., in areas inappropriate for drone surveying) for generating precise and accurate spatial intelligence to support operational LSM programmes.

An unsupervised method for social network spammer detection based on user information interests

Online Social Networks (OSNs) are a popular platform for communication and collaboration. Spammers are highly active in OSNs. Uncovering spammers has become one of the most challenging problems in OSNs. Classification-based supervised approaches are the most commonly used method for detecting spammers. Classification-based systems suffer from limitations of “data labelling”, “spam drift”, “imbalanced datasets” and “data fabrication”. These limitations effect the accuracy of a classifier’s detection. An unsupervised approach does not require labelled datasets. We aim to address the limitation of data labelling and spam drifting through an unsupervised approach.We present a pure unsupervised approach for spammer detection based on the peer acceptance of a user in a social network to distinguish spammers from genuine users. The peer acceptance of a user to another user is calculated based on common shared interests over multiple shared topics between the two users. The main contribution of this paper is the introduction of a pure unsupervised spammer detection approach based on users’ peer acceptance. Our approach does not require labelled training datasets. While it does not better the accuracy of supervised classification-based approaches, our approach has become a successful alternative for traditional classifiers for spam detection by achieving an accuracy of 96.9%.

Analysis of Deforested Area Using Google Earth Engine in The Period 2001-2020 In the Apurimac Region

The objective of this study is to analyze the deforestation of forest cover in the Apurimac region between 2001 and 2020 using the Google Earth Engine (GEE) platform, a planetary-scale platform for the analysis of environmental data. The methodology used in the analysis of the deforested area is based on the classification of cover, using a supervised classification method developed by the University of Maryland, based on a "decision tree".

Improved Active Deep Learning for Semi-Supervised Classification of Hyperspectral Image

Hyperspectral image (HSI) data classification often faces the problem of the scarcity of labeled samples, which is considered to be one of the major challenges in the field of remote sensing. Although active deep networks have been successfully applied in semi-supervised classification tasks to address this problem, their performance inevitably meets the bottleneck due to the limitation of labeling cost. To address the aforementioned issue, this paper proposes a semi-supervised classification method for hyperspectral images that improves active deep learning. Specifically, the proposed model introduces the random multi-graph algorithm and replaces the expert mark in active learning with the anchor graph algorithm, which can label a considerable amount of unlabeled data precisely and automatically. In this way, a large number of pseudo-labeling samples would be added to the training subsets such that the model could be fine-tuned and the generalization performance could be improved without extra efforts for data manual labeling. Experiments based on three standard HSIs demonstrate that the proposed model can get better performance than other conventional methods, and they also outperform other studied algorithms in the case of a small training set.

ANÁLISE DA EVOLUÇÃO DO USO E OCUPAÇÃO DAS TERRAS NO ARRONDISSEMENT DE ARCAHAIE-HAITI (1987, 1997 E 2018)

Atualmente, utiliza-se os recursos da natureza de forma exploratória, sem a projeção dos impactos que essa atitude pode ocasionar, gerando problemas de caráter social e/ou ambiental, podendo apresentar seus efeitos rapidamente ou em grande escala de tempo. No Haiti, constata-se que a região possui incapacidade de enfrentar qualquer problema de caráter ambiental, essa situação está relacionada diretamente com as atividades antrópicas. Nesse sentido, a presente pesquisa teve como objetivo analisar a evolução temporal do uso e ocupação da terra do Arrondissement de Arcahaie, localizada a Oeste do Haiti. O Arrondissement é uma divisão administrativa do território haitiano que é composta por vários municípios. O método utilizado foi uma fotointerpretação sobre o recorte das Imagens Landsat 5 e Landsat 8, referente a área de estudo. Para o mapeamento foi utilizada a classificação supervisionada. As classes de uso e ocupação definidas foram: pastagem, cobertura vegetal, solo exposto, área cultivada, área urbana, mata natural. Os resultados mais significativos mostram mudanças na dinâmica de uso e ocupação da terra no Arrondissement de Arcahaie, durante 31 anos e consequentemente, podendo causar danos, muitas vezes, irreversíveis ao meio ambiente e comprometer a qualidade de vida da população. EVOLUTION ANALYSIS OF THE LAND USE AND OCCUPATION IN ARRONDISSEMENT OF ARCAHAIE-HAITI (1987, 1997 AND 2018)A B S T R A C TCurrently, the nature resources are used in an exploratory way, without the projection of the impacts that this attitude can cause, generating social and / or environmental problems, can present their effects quickly or in a large scale of time. In Haiti, it appears that their inability to face any environmental problem is directly related to anthropic activities. In this sense, the present research had as main objective to analyze the temporal evolution of the use and occupation of the land of the Arrondissement of Arcahaie, located to the West of Haiti. The Arrondissement is an administrative division of Haitian territory that decomposes several municipalities. The method used was a photointerpretation on the clipping of the Landsat 5 and Landsat 8 images, referring to the study area. Supervised classification was used for the mapping. The classes of use and occupation defined were pasture, vegetation cover, exposed soil, cultivated area, urban area, natural forest. The most significant results show changes in the dynamics of use and occupation in the Arrondissement of Arcahaie during the last 31 years and, consequently, can cause damage, often irreversible to the environment and compromise the quality of life of the population.Key words: Environmental impacts, Natural resources, Arrondissement of Arcahaie

Identificação das Dunas do Atacama (Norte do Chile) a partir da avaliação de três algoritmos no Google Earth Engine

As dunas correspondem a processos de sedimentação eólica, que podem estar tanto nas áreas costeiras marinhas, como no interior do continente com algumas diferenças na modelagem. No Sul do deserto do Atacama, no Norte do Chile, há um conjunto de seis campos de dunas intermontanhas chamadas Mar de Dunas do Atacama, as quais têm tipologias complexas de dunas do deserto, que podem ser ativas, semiativas ou estabilizadas. O seu monitoramento é conveniente para conhecer detalhes sobre a possível invasão de areias das dunas ao sul do rio Copiapó. Dessa forma, esta pesquisa tem como objetivo avaliar os métodos de classificação supervisionada Random Forest, CART e SmileCART através de duas metodologias de amostragens, aleatória e estratificada, numa imagem Landsat 5 na plataforma em nuvem Google Earth Engine, a fim de verificar qual método oferece o melhor resultado para o mapeamento do Mar de Dunas do Atacama. Para conseguir este objetivo, foram criados polígonos de classes para a realização da amostragem aleatória estratificada e chave de interpretação para amostragem aleatória simples. O processo de avaliação da acurácia foi feito através de imagem Sentinel 2 com a aplicação dos índices de Simultaneidade Geográfica, Erros de Comissão e Omissão, e Exatidão Global. Observou-se como resultados para os algoritmos testados, que os três algoritmos foram eficientes para o mapeamento das Dunas do Atacama, entretanto, a técnica de classificação supervisionada por CART, com a metodologia da amostragem aleatória simples, representou o melhor desempenho. Identification of the Atacama Dunes (Northern Chile) from the evaluation of three algorithms on Google Earth EngineA B S T R A C TThe dunes correspond to wind sedimentation processes, which can be found both in marine coastal areas and in the interior of the continent with some differences in modeling. In the south of the Atacama desert, in northern Chile, there are a set of six inter-mountain dune fields called Mar de Dunas do Atacama, which have complex types of desert dunes, which can be active, semi-active or stabilized. Its monitoring is convenient to know details about the possible invasion of sand from the dunes south of the Copiapó River. Thus, this research aims to evaluate the supervised classification methods Random Forest, CART and SmileCART through two sampling methodologies, random and stratified, in a Landsat 5 image on the Google Earth Engine cloud platform, in order to verify which method offers the best result for mapping the Atacama Dunes Sea. In order to achieve this objective, class polygons were created to perform stratified random sampling and the interpretation key for simple random sampling. The accuracy assessment process was performed using a Sentinel 2 image with the application of the Geographic Simultaneity indices and the Commission and Omission Errors. It was observed as results for the tested algorithms, that the three algorithms were efficient for mapping the Atacama Dunes, however, the CART supervised classification technique, with the simple random sampling methodology, represents the best performance.

KESESUAIAN LAHAN PERMUKIMAN TERHADAP RENCANA TATA RUANG WILAYAH BERBASIS SIG DI KABUPATEN KEPULAUAN SANGIHE

The problem in this study is related to the number of developments, especially those aimed at their designation, which is not by the existing regional spatial plan. This is because many developments are located in disaster-prone areas, coastal border areas, and protected areas. This also triggers changes in land use that are quite large from time to time. This study aims to determine the use of utilization with a regional spatial plan. This study uses quantitative methods to determine developments based on data in the Sangihe Islands Regency, analyzing image data and knowing the level of suitability of land use with the RTRW. The method of analysis in this study uses a method of spatial analysis based on geographic information systems (GIS) using supervised classification, scoring, weighting, overlay. The variables in this study include land use, spatial planning, and adjustments. The results show that the land area in the Regional Spatial Plan is suitable for land use in particular for an area of ​​3,202.65 hectares and not suitable for an area of ​​17,946.03 hectares from the total area of ​​the existing land use.