Research Article
Automated Lunar Surface Image Classification Using Deep Convolutional Neural Networks for Geological Feature Detection
J M Raisul Islam Shohag*
Issue:
Volume 10, Issue 2, December 2024
Pages:
27-35
Received:
27 September 2024
Accepted:
17 October 2024
Published:
31 October 2024
Abstract: Robotic rovers have vastly expanded our understanding of the lunar surface, providing detailed imagery crucial for scientific research and future exploration. However, manually classifying this imagery is time-consuming and prone to errors, necessitating automated solutions. Automated classification of lunar surface imagery is vital for efficient data analysis, site selection for future missions, and advancing lunar exploration. Developing accurate and efficient image classification systems tailored for lunar terrain is thus imperative. The objective of this study is to develop and assess an image classification system utilizing Deep Convolutional Neural Networks (DCNNs) specifically for lunar surface images. The aim is to achieve high accuracy and efficiency in identifying geological features such as craters and dunes, as observed by robotic rovers. A curated dataset of lunar surface images was partitioned into training, testing, and validation subsets. DCNNs models were trained on the training dataset and evaluated using testing and validation datasets. Hyperparameter tuning and optimization techniques were employed to enhance model performance. The classification system based on DCNNs showed promising outcomes. Model B and F achieved an accuracy of 91.1%, while Model A and D achieved 87.5%. Model C attained an accuracy of 89.3%, and Model E reached 83.9%. Visualizations of training and validation metrics revealed distinct performance patterns across models, highlighting the potential for further advancements in lunar exploration research.
Abstract: Robotic rovers have vastly expanded our understanding of the lunar surface, providing detailed imagery crucial for scientific research and future exploration. However, manually classifying this imagery is time-consuming and prone to errors, necessitating automated solutions. Automated classification of lunar surface imagery is vital for efficient d...
Show More
Research Article
Knowledge Exchange Between Neural Network Toward Dawn of Language
Seisuke Yanagawa*
Issue:
Volume 10, Issue 2, December 2024
Pages:
36-43
Received:
2 October 2024
Accepted:
21 October 2024
Published:
26 November 2024
Abstract: In this paper, the nervous system is composed of a combination of common structure components, indicating that the hierarchical structure may lead to a great evolution to cognitive function extending eating behavior. The common component (basic unit) is a set that combines neural circuits to cylindrical forms, and the basic unit has an affinity with the structure of pillars, barrels, or blobs in neuroscience. Use multiple input and output to achieve a variable value function. By connecting a basic unit in a hierarchically, it can be done more complex time -series data process and can be add almost unlimited. Time series data is saved by repeating judgment and action. Save data includes not only food and other objects, but also surrounding situations. If the new situation resembles the elements of the time that is already recorded, the approximation element becomes active and the activation spreads throughout the past time series data. Time series data is constantly updated with processing. As example, reality turns into a new cause, and prediction turns into a new reality. If the two areas are often active at the same time, even if only one area becomes active, the corresponding areas will also change. This learning function corresponds to Hebb's law in neuroscience. This feature is the basis of imitation and conditional learning, enabling people to communicate with fellows and enabling collective actions. This ability is an indispensable ability to build a society and is the beginning of a language. Languages can express events not only in the past or future events, but also in places where sensory organs cannot reach. It has been inherited for generations as a culture. In this paper, a new layer is proposed at the top of the neural network that has evolved from eating behavior. The processing of the new layer is asynchronous with the lower layer, but it performs a complementary process and enables event communication with friends. This ability is the basics of language. The process of forming common knowledge exchanging questions and teachings between two neural networks is shown a simple example.
Abstract: In this paper, the nervous system is composed of a combination of common structure components, indicating that the hierarchical structure may lead to a great evolution to cognitive function extending eating behavior. The common component (basic unit) is a set that combines neural circuits to cylindrical forms, and the basic unit has an affinity wit...
Show More
