Author(s): Guo D; Luo Z; Bouguila N; Fan W;

Neural topic models (NTMs) based on variational autoencoders (VAEs) have emerged as a scalable and flexible alternative to classical probabilistic models for uncovering latent thematic structures in text corpora. However, most existing NTMs either overlook the geometric structure of word embeddings or rely on Euclidean priors that are poorly aligned with ...

Article GUID: 41791177

Author(s): Li Z; Luo Z; Bouguila N; Su W; Fan W;

Multi-view clustering has gained significant attention due to its ability to integrate data from diverse perspectives, frequently outperforming single-view approaches. However, existing methods often assume a Gaussian distribution within the latent embedding space, which can degrade performance when handling high-dimensional data or data with complex, non ...

Article GUID: 40664160

Author(s): Rajagopal R; Bele V; Saady NMC; Hickmann FMW; Goyette B;

The objective of this study was to obtain start-up strategies for the operation of a dry anaerobic digestion (DAD) system treating pig-manure (PM) solids at low-temperatures, and evaluate the effects of operation mode, adapted inoculum, and bedding material on the performance. A DAD system coupled with an inoculum system (two-stage DAD) was operated at 20 ...

Article GUID: 36134981