-
Article
Unsupervised image categorization based on deep generative models with disentangled representations and von Mises-Fisher distributions
Variational autoencoders (VAEs) have emerged as powerful deep generative models for learning abstract representations in the latent space, making them highly applicable across diverse domains. This paper prese...
-
Article
A scaled dirichlet-based predictive model for occupancy estimation in smart buildings
In this study, we introduce a predictive model leveraging the scaled Dirichlet mixture model (SDMM). This data-driven approach offers enhanced accuracy in predictions, especially with a limited training datase...
-
Article
Law of the damp heat in mines and its application exploration based on FST
In the process of development and utilization of mine resources, the damp-heat environment has always been a difficult problem for mining. An enormous amount of research effort has gone into analyzing the unde...
-
Article
Deep generative clustering methods based on disentangled representations and augmented data
This paper presents a novel clustering approach that utilizes variational autoencoders (VAEs) with disentangled representations, enhancing the efficiency and effectiveness of clustering. Traditional VAE-based ...
-
Article
Optimal control of a two-phase heterogeneous service retrial queueing system with collisions and delayed vacations
This paper proposes a novel two-phase heterogeneous service retrial queueing system with collisions and delayed vacations. We consider services for two types of customers: ordinary customers (service completed...
-
Article
Open AccessATP6AP1 as a potential prognostic biomarker in CRC by comprehensive analysis and verification
The role of ATP6AP1 in colorectal cancer (CRC) remains elusive despite its observed upregulation in pan-cancer. Therefore, the current study aimed to assess the clinical significance of ATP6AP1 and its relatio...
-
Article
Open AccessThe impact of SLC10A3 on prognosis and immune microenvironment in colorectal adenocarcinoma
SLC10A3, a gene upregulated in pan-cancer, lacks full understanding regarding its prognostic implications and association with immune infiltration in colorectal cancer (CRC). This study comprehensively analyze...
-
Chapter and Conference Paper
An ANN-Guided Approach to Task-Free Continual Learning with Spiking Neural Networks
Task-Free Continual Learning (TFCL) poses a formidable challenge in lifelong learning, as it operates without task-specific information. Leveraging spiking neural networks (SNNs) for TFCL is particularly intri...
-
Article
Transformer-based contrastive learning framework for image anomaly detection
Anomaly detection refers to the problem of uncovering patterns in a given data set that do not conform to the expected behavior. Recently, owing to the continuous development of deep representation learning, a...
-
Article
Unsupervised meta-learning via spherical latent representations and dual VAE-GAN
Unsupervised learning and meta-learning share a common goal of enhancing learning efficiency compared to starting from scratch. However, meta-learning methods are predominantly employed in supervised settings,...
-
Article
Occupancy estimation in smart buildings using predictive modeling in imbalanced domains
This paper introduces a novel approach for occupancy estimation in smart buildings. In particular, we focus on the challenging yet common situation where the amount of training data is small and imbalanced (i....
-
Article
Cross-collection latent Beta-Liouville allocation model training with privacy protection and applications
Cross-collection topic models extend previous single-collection topic models, such as Latent Dirichlet Allocation (LDA), to multiple collections. The purpose of cross-collection topic modeling is to model docu...
-
Article
Continuous image anomaly detection based on contrastive lifelong learning
With the development of deep learning techniques, an increasing number of anomaly detection methods based on deep neural networks have been proposed during the last decade. Nevertheless, these methods often su...
-
Article
Polyvinylammonium-immobilized FAPbI3 Perovskite Grains for Flexible Fibrous Woven RRAM Array
Woven resistive random access memory (RRAM) is a promising subject in flexible wearable electronic devices. In this work, polyvinylammonium iodate (PVAm·HI) is added to the FAPbI3 perovskite precursor solution to...
-
Chapter and Conference Paper
Analysis of Network Loss Influence Characteristics of Distribution Network with Different Types of DG
Grid connection of large-scale distributed power sources has become an integral part of the development of a new power system and the achievement of “dual carbon” goals. DG access on a large scale leads to the...
-
Chapter and Conference Paper
Unsupervised Disentanglement Learning via Dirichlet Variational Autoencoder
Unsupervised disentanglement learning is the process of discovering factorized variables that include interpretable semantic information and encode separate factors of variations in the data. It is a critical ...
-
Chapter and Conference Paper
A Contrastive Method for Continual Generalized Zero-Shot Learning
Generalized zero-shot learning (GZSL) aims to train a model that can classify seen and unseen samples based on semantic information. Continual learning, as one of the factors distinguishing artificial intellig...
-
Chapter and Conference Paper
A Selective Supervised Latent Beta-Liouville Allocation for Document Classification
We propose a novel model, selective supervised Latent Beta-Liouville (ssLBLA), that improves the performance and generative process of supervised probabilistic topic models with a more flexible prior and simpl...
-
Chapter and Conference Paper
Spiking Generative Networks in Lifelong Learning Environment
Spiking neural networks (SNNs) have gained popularity due to their ability to operate at ultra-high speed and ultra-low power consumption, making them suitable for energy-efficient applications in various fiel...
-
Article
Unsupervised modeling and feature selection of sequential spherical data through nonparametric hidden Markov models
As spherical data (i.e. \(L_2\) L 2 ...
