A Hybrid Classification of Imbalanced Hyperspectral Images Using ADASYN and Enhanced Deep Subsampled Multi-Grained Cascaded Forest

Datta, Debaleena; Mallick, Pradeep Kumar; Reddy, Annapareddy V. N.; Mohammed, Mazin Abed; Jaber, Mustafa Musa; Alghawli, Abed Saif; Al-qaness, Mohammed A. A.

doi:10.3390/rs14194853

Cited by 12 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Para isso, o ADASYN utiliza uma distribuic ¸ão de densidade como critério para decidir automaticamente o número de amostras sintéticas que precisam ser geradas para cada exemplo minoritário. Como resultado, os dados sintéticos adicionais são gerados para exemplos da classes minoritária que são mais difíceis de aprender [30].…”

Section: Adasynunclassified

Rede neural artificial para predição de brucelose bovina a partir de dados desbalanceados

Queiroz Alves,

Ferreira,

Fortunato

et al. 2024

Anais Do XVI Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

The expressiveness of Brazilian livestock is unquestionable. According to data from the United States Department of Agriculture (USDA), in 2021 Brazil was the worlds largest exporter of beef. Bovine brucellosis is one of the most worrying diseases for the sector. In Brazil, bovine brucellosis causes annual losses of around 448 million dollars. Several factors threaten the establishment of actions of the current animal defense programs in Brazil, the main ones being: lack of distinct guidelines for the diagnosis of brucellosis cases, infected animals remain asymptomatic when infected, extensive Brazilian territory and large number of herds. The use of Artificial Neural Networks (ANNs) can be very useful in health and epidemiological surveillance services, helping to screen properties with different risks for the disease. The objective of this work is the development of ANN with class balancing techniques and selection of variables via genetic algorithm, for the classification and segregation of bovine herds, regarding seroprevalence for brucellosis. Five ANNs were designed combining different approaches of class balancing technique and variable selection, in order to compare which approach would perform better results. The results showed that ANN combined with the variable selection technique, via Genetic Algorithms, and class balancing, is a promising approach.

show abstract

Section: Adasynunclassified

Rede neural artificial para predição de brucelose bovina a partir de dados desbalanceados

Queiroz Alves,

Ferreira,

Fortunato

et al. 2024

Anais Do XVI Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

show abstract

“…Remote sensing data classification has research significance in the fields of urban planning , mining exploration, and agriculture [1][2][3][4][5]. In recent years, with the rapid development of sensor technology, a variety of remote sensing data sources have been provided to support remote sensing data classification tasks.…”

Section: Introductionmentioning

confidence: 99%

Causal Meta-Reinforcement Learning for Multimodal Remote Sensing Data Classification

Zhang,

Wang,

Wang

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Multimodal remote sensing data classification can enhance a model’s ability to distinguish land features through multimodal data fusion. In this context, how to help models understand the relationship between multimodal data and target tasks has become the focus of researchers. Inspired by the human feedback learning mechanism, causal reasoning mechanism, and knowledge induction mechanism, this paper integrates causal learning, reinforcement learning, and meta learning into a unified remote sensing data classification framework and proposes causal meta-reinforcement learning (CMRL). First, based on the feedback learning mechanism, we overcame the limitations of traditional implicit optimization of fusion features and customized a reinforcement learning environment for multimodal remote sensing data classification tasks. Through feedback interactive learning between agents and the environment, we helped the agents understand the complex relationships between multimodal data and labels, thereby achieving full mining of multimodal complementary information.Second, based on the causal inference mechanism, we designed causal distribution prediction actions, classification rewards, and causal intervention rewards, capturing pure causal factors in multimodal data and preventing false statistical associations between non-causal factors and class labels. Finally, based on the knowledge induction mechanism, we designed a bi-layer optimization mechanism based on meta-learning. By constructing a meta training task and meta validation task simulation model in the generalization scenario of unseen data, we helped the model induce cross-task shared knowledge, thereby improving its generalization ability for unseen multimodal data. The experimental results on multiple sets of multimodal datasets showed that the proposed method achieved state-of-the-art performance in multimodal remote sensing data classification tasks.

show abstract

“…Remote sensing data classification has important research significance in the fields of urban planning , mining exploration, and agriculture [1][2][3][4][5]. In recent years, with the rapid development of sensor technology, a variety of remote sensing data sources have been provided to support remote sensing data classification tasks.…”

Section: Introductionmentioning

confidence: 99%

Causal Meta-Reinforcement Learning for Multimodal Remote Sensing Data Classification

Zhang,

Wang,

Wang

et al. 2024

Preprint

View full text Add to dashboard Cite

Multimodal remote sensing data classification can enhance the model’s ability to distinguish land features through multimodal data fusion. In this context, how to help models understand the relationship between multimodal data and target tasks is the focus of researchers. Inspired by human feedback learning mechanisms, causal reasoning mechanisms, and knowledge induction mechanisms, this paper integrates causal learning, reinforcement learning, and meta learning into a unified remote sensing data classification framework and proposed the causal meta-reinforcement learning (CMRL). First, based on feedback learning mechanisms, we have overcome the limitations of traditional implicit optimization of fusion features and customized a reinforcement learning environment for multimodal remote sensing data classification tasks. Through feedback interactive learning between agents and the environment, we help them understand the complex relationships between multimodal data and labels, thereby achieving full mining of multimodal complementary information. Second, based on the causal inference mechanism we designed causal distribution prediction action, classification reward, and causal intervention reward, capturing pure causal factors in multimodal data and cutting off false statistical associations between non-causal factors and class labels. Finally, based on the knowledge induction mechanism, we designed a bi-layer optimization mechanism based on meta-learning. By constructing a meta training task and meta validation task simulation model in the generalization scenario of unseen data, we helped the model induce cross-task shared knowledge, thereby improving its generalization ability for unseen multimodal data. The experimental results on multiple sets of multimodal datasets show that the proposed method achieved state-of-the-art performance in multimodal remote sensing data classification tasks.

show abstract

A Hybrid Classification of Imbalanced Hyperspectral Images Using ADASYN and Enhanced Deep Subsampled Multi-Grained Cascaded Forest

Cited by 12 publications

References 27 publications

Rede neural artificial para predição de brucelose bovina a partir de dados desbalanceados

Rede neural artificial para predição de brucelose bovina a partir de dados desbalanceados

Causal Meta-Reinforcement Learning for Multimodal Remote Sensing Data Classification

Causal Meta-Reinforcement Learning for Multimodal Remote Sensing Data Classification

Contact Info

Product

Resources

About