Automatic ship classification for a riverside monitoring system using a cascade of artificial intelligence techniques including penalties and rewards

Połap, Dawid; Wlodarczyk–Sielicka, Marta; Wawrzyniak, Natalia

doi:10.1016/j.isatra.2021.04.003

Cited by 34 publications

(15 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Firstly, the aggregation operator proposed in this study can be extended into other neutrosophic sets such as vague neutrosophic set, neutrosophic soft set and many others. Secondly, it may be possible to consider the applications of the proposed method to tackle the current real issues such as in automatic ship classification (Połap et al 2021 ), coastal erosion (Awang et al 2019a , b ), energy policy (Jamil and Rashid 2018 ) and covid-19 decision-making (Albahri et al 2020 ). The common feature of these real-world problems is the interdependence of multiple criteria and different weights.…”

Section: Discussionmentioning

confidence: 99%

A Bonferroni mean considering Shapley fuzzy measure under hesitant bipolar-valued neutrosophic set environment for an investment decision

Awang

Abdullah

Hashim

2021

J Ambient Intell Human Comput

View full text Add to dashboard Cite

Bonferroni mean (BM) operators have been established as a powerful tool for handling the interrelationship between the input arguments under various decision-making information. However, the existing BM operators do not take into account the overall interaction among decision makers or criteria. To overcome this limitation, this study considers the Shapley fuzzy measure (SFM) with the normalized weighted BM (NWBM) operator under a neutrosophic environment. In addition, the current research ignores the bipolarity and hesitancy during decision elicitations, resulting in the imprecise decision results. In this paper, the hesitant bipolar-valued neutrosophic set (HBNS) which is the extension of hesitant fuzzy set and bipolar neutrosophic set is employed. The main focus of this paper is in the development of an aggregation operator for HBNS. Based on the literature review, we would like to fill in the gaps by developing a hesitant bipolar-valued neutrosophic Shapley NWBM (HBN-SNWBM) operator where the overall interaction among decision makers can be considered. Besides that, a three-phase decision making framework is also proposed to show the applicability of the proposed aggregation operator to the real-world decision problems. The HBN-SNWBM operator and the decision making framework are applied to two examples of investment selection where evaluations are implemented using the proposed aggregations that based upon hesitant bipolar-valued neutrosophic sets. In the first example, it is found that a weapon company is the best alternative for investment followed by a food company. Sensitivity of parameters of the aggregation operator is also analysed and it is found that the ranking results are consistent despite of different parameter values used. This verifies the insensitivity of p,q parameters in the developed aggregation operator. The proposed decision making framework and hesitant bipolar-valued neutrosophic sets would be a great significance for the practical implementation of the aggregation operators.

show abstract

Section: Discussionmentioning

confidence: 99%

A Bonferroni mean considering Shapley fuzzy measure under hesitant bipolar-valued neutrosophic set environment for an investment decision

Awang

Abdullah

Hashim

2021

J Ambient Intell Human Comput

View full text Add to dashboard Cite

show abstract

“…However, these features rely heavily on manual design and do not validly depict the semantic message to achieve excellent classification outcomes. Along with the evolution of artificial intelligence, it has been widely used in many fields, such as automatic ship classification based on a variety of artificial intelligence technologies [13], and remote-sensing image analysis tasks [14]. Better results have been acquired for remote-sensing image scene classification using convolutional neural network (CNN) methodologies [15][16][17][18].…”

Section: Introductionmentioning

confidence: 99%

Remote Sensing Image Scene Classification Based on Global Self-Attention Module

Yan

2021

Remote Sensing

View full text Add to dashboard Cite

The complexity of scene images makes the research on remote-sensing image scene classification challenging. With the wide application of deep learning in recent years, many remote-sensing scene classification methods using a convolutional neural network (CNN) have emerged. Current CNN usually output global information by integrating the depth features extricated from the convolutional layer through the fully connected layer; however, the global information extracted is not comprehensive. This paper proposes an improved remote-sensing image scene classification method based on a global self-attention module to address this problem. The global information is derived from the depth characteristics extracted by the CNN. In order to better express the semantic information of the remote-sensing image, the multi-head self-attention module is introduced for global information augmentation. Meanwhile, the local perception unit is utilized to improve the self-attention module’s representation capabilities for local objects. The proposed method’s effectiveness is validated through comparative experiments with various training ratios and different scales on public datasets (UC Merced, AID, and NWPU-NESISC45). The precision of our proposed model is significantly improved compared to other methods for remote-sensing image scene classification.

show abstract

“…Thanks to neural networks' powerful representation capabilities, it has been widely used in image recognition and has shown excellent performance [4][5][6][7]. Połap et al [8] applied convolutional neural networks (CNNs) to the monitoring system on the river, using a cascade of artificial intelligence techniques including penalties and rewards. Similar approaches were based on a neural bag-of-words mechanism.…”

Section: Introductionmentioning

confidence: 99%

“…Połap et al. [8] applied convolutional neural networks (CNNs) to the monitoring system on the river, using a cascade of artificial intelligence techniques including penalties and rewards. Similar approaches were based on a neural bag‐of‐words mechanism.…”

Section: Introductionmentioning

confidence: 99%

MAM: A multipath attention mechanism for image recognition

Zhang

Peng

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

Attention mechanism has shown excellent performance in many computer vision tasks, while the previous literature may not adequately consider different types of attention mechanisms or is individual elaborate designed for a certain network. In this paper, a general yet effective multipath attention mechanism (MAM) to explore the effect of visual attention for image recognition is proposed. In contrast with other attentions that leverage global pooling, the main advantage is that the MAM considers both the correlation of featuremaps and different scale structural information into account. The backbone representations are enhanced by adding MAM laterally along independent and separate dimensions, channel and spatial. Due to only a simple and unified calculation block is generated, MAM can be flexibly integrated into various CNNs within few parameters and trained together end‐to‐end. Furthermore, the topology structures of attention path arrangement are investigated using different connection schemes. Experimental results on several image recognition datasets show that the model outperforms various existing models. Finally, performance improvement through visualisation is intuitively discussed. The source code for the proposed attention module is publicly available.

show abstract

Automatic ship classification for a riverside monitoring system using a cascade of artificial intelligence techniques including penalties and rewards

Cited by 34 publications

References 19 publications

A Bonferroni mean considering Shapley fuzzy measure under hesitant bipolar-valued neutrosophic set environment for an investment decision

A Bonferroni mean considering Shapley fuzzy measure under hesitant bipolar-valued neutrosophic set environment for an investment decision

Remote Sensing Image Scene Classification Based on Global Self-Attention Module

MAM: A multipath attention mechanism for image recognition

Contact Info

Product

Resources

About