In this paper, we propose a high performance Two-Stream spectral-spatial Residual Network (TSRN) for hyperspectral image classification. The first spectral residual network (sRN) stream is used to extract spectral characteristics, and the second spatial residual network (saRN) stream is concurrently used to extract spatial features. The sRN uses 1D convolutional layers to fit the spectral data structure, while the saRN uses 2D convolutional layers to match the hyperspectral spatial data structure. Furthermore, each convolutional layer is preceded by a Batch Normalization (BN) layer that works as a regularizer to speed up the training process and to improve the accuracy. We conducted experiments on three well-known hyperspectral datasets, and we compare our results with five contemporary methods across various sizes of training samples. The experimental results show that the proposed architecture can be trained with small size datasets and outperforms the state-of-the-art methods in terms of the Overall Accuracy, Average Accuracy, Kappa Value, and training time.

Fishery has contributed a lot to Indonesian economy development such as domestic industries, micro industries, and export industries. Tuna is one of the fishery product. To produce tuna fish product, an industry must separate tuna based on their type. Nowadays, the separation process is still done manually. As consequence, the process was slow and the error rate was high. This research proposed automatic tuna fish classification using decision tree algorithm and image processing method. Eight features, texture feature and shape feature, were extracted from tuna fish image using image processing method. The texture features are contrast, correlation, energy, homogeneity, inverse difference moment, and entropy. While the shape features are the circular rate of tuna's head and the ratio of head area and circular area. These features are then used to create classification model using decision tree. Sixty tuna's image from tree types tuna, Bigeye, Yellowfin, and Skipjack, were used in experiment. From experiment, it shows that the average accuracy of the classification is 88%.

Biotic and abiotic plant stress (e.g., frost, fungi, diseases) can significantly impact crop production. It is thus essential to detect such stress at an early stage before visual symptoms and damage become apparent. To this end, this paper proposes a novel deep learning method, called Spectral Convolution and Channel Attention Network (SC-CAN), which exploits the difference in spectral responses of healthy and stressed crops. The proposed SC-CAN method comprises two main modules: (i) a spectral convolution module, which consists of dilated causal convolutional layers stacked in a residual manner to capture the spectral features; (ii) a channel attention module, which consists of a global pooling layer and fully connected layers that compute inter-relationship between feature map channels before scaling them based on their importance level (attention score). Unlike standard convolution, which focuses on learning local features, the dilated convolution layers can learn both local and global features. These layers also have long receptive fields, making them suitable for capturing long dependency patterns in hyperspectral data. However, because not all feature maps produced by the dilated convolutional layers are important, we propose a channel attention module that weights the feature maps according to their importance level. We used SC-CAN to classify salt stress (i.e., abiotic stress) on four datasets (Chinese Spring (CS), Aegilops columnaris (co(CS)), Ae. speltoides auchery (sp(CS)), and Kharchia datasets) and Fusarium head blight disease (i.e., biotic stress) on Fusarium dataset. Reported experimental results show that the proposed method outperforms existing state-of-the-art techniques with an overall accuracy of 83.08%, 88.90%, 82.44%, 82.10%, and 82.78% on CS, co(CS), sp(CS), Kharchia, and Fusarium datasets, respectively.

This article introduces a two-phase learning approach for hyperspectral image (HSI) classification using few-shot learning (FSL). For the first phase, we present a novel spatiospectral masked autoencoder (ssMAE)—an advanced self-supervised learner. For the ssMAE backbone network, we designed a transformer encoder-decoder network, where we replaced the linear layer that is used as the initial feature embedding with a 3-D convolutional layer to better extract local spectral-spatial features from 3-D visible sub-patches. By tapping into vast unlabeled data, the ssMAE learns general HSI features. In the second phase, the ssMAE encoder is fine-tuned to extract discriminative features for classification using the few-shot labeled training samples. This is achieved through a unique hybrid episode learning method that integrates the ssMAE encoder in a prototypical network (PN). We innovate with a mix of global and local prototypes (combined global-local (CGL) prototype) to refine label predictions. This technique maximizes data usage, focuses on specific samples, and mitigates issues from subpar episodes. Tested on three HSI datasets, our approach outperforms alternative few-shot methods. The code will be made publicly available at https://github.com/Weejaa04/SSMAE.

The Augmented Reality (AR) is a technology that integrates a digital information with the user's environment in the real-time or the view of the physical real-world environment whose elements are augmented by computer-generated sensory input e.g. image/graphics, GPS data, sound or video. The AR technology uses the existing real environment and overlays a new digital information on top of it. There are many AR application developed in many aspects of life e.g. health, education, military, industry, entertainment, etc. This research explores the location-based AR technology to develop a game named Monster Buster. This game is an Android platform. This game uses the information of latitude and longitude used to generate the position of the monster. This research is expected to develop an innovative game application that can give another user's experience by using the location-based AR technology. The Unity 3D is the game engine that is used in this research, and the Kudan SDK is used to provide the AR technology.