Hyperspectral image and LiDAR image fusion plays a crucial role in remote sensing by capturing spatial relationships and modeling semantic information for accurate classification and recognition. However, existing methods, like Graph Convolutional Networks (GCNs), face challenges in constructing effective graph structures due to variations in local semantic information and limited receptiveness to large-scale contextual structures. To overcome these limitations, we proposed a invariant attribute-driven binary bi-branch classification (IABC) method which is a unified network that combines binary Convolutional Neural Network (CNN) and GCN with invariant attributes. Our approach utilizes a joint detection framework that can simultaneously learn features from small-scale regular regions and large-scale irregular regions, resulting in an enhanced structured representation of HSI and LiDAR images in the spectral-spatial domain. This approach not only improves the accuracy of classification and recognition but also reduces storage requirements and enables real-time decision-making, which is crucial for effectively processing large-scale remote sensing data. Extensive experiments demonstrates the superior performance of our proposed method in hyperspectral image analysis tasks. The combination of CNNs and GCNs allows for accurate modeling of spatial relationships and effective construction of graph structures. Furthermore, the integration of binary quantization enhances computational efficiency, enabling real-time processing of large-scale data. Therefore, our approach presents a promising opportunity for advancing remote sensing applications using deep learning techniques.

The emergence of Artificial Intelligence (AI) driven Keyword Spotting (KWS) technologies has revolutionized human to machine interaction. Yet, the challenge of end-to-end energy efficiency, memory footprint and system complexity of current Neural Network (NN) powered AI-KWS pipelines has remained ever present. This paper evaluates KWS utilizing a learning automata powered machine learning algorithm called the Tsetlin Machine (TM). Through significant reduction in parameter requirements and choosing logic over arithmetic based processing, the TM offers new opportunities for low-power KWS while maintaining high learning efficacy. In this paper we explore a TM based keyword spotting (KWS) pipeline to demonstrate low complexity with faster rate of convergence compared to NNs. Further, we investigate the scalability with increasing keywords and explore the potential for enabling low-power on-chip KWS.

Broad bean paste (BBP) is a traditional fermented soy food, and its high salt content not only prolongs the fermentation time but also threatens human health. In this study, three BBP-meju with different salt concentrations were prepared, and the effects of varying salinity on the fermentation process were comprehensively compared. The results showed that salt-reduced fermentation contributed to the accumulation of amino acid nitrogen, reducing sugars, free amino acids, and organic acids. Alcohols, esters, aldehydes, and acids were the main volatile flavor compounds in BBP-meju, and the highest total volatile flavor compounds were found in medium-salt meju. Bacillus, Staphylococcus, Aspergillus, and Mortierella were the dominant microbial communities during fermentation, and there were also three opportunistic pathogens, Enterobacter, Pantoea, and Brevundimonas, respectively. According to Spearman correlation analysis, Wickerhamomyces, Bacillus, Staphylococcus, and Mortierella all showed highly significant positive correlations with ≥3 key flavor compounds, which may be the core functional flora. Furthermore, the dominant microbial genera worked synergistically to promote the formation of high-quality flavor compounds and inhibit the production of off-flavors during salt-reduced fermentation. This study provides a theoretical reference for the quality and safety control of low-salt fermented soy foods.