Skip to Content

1,182 Results Found

  • Article
  • Open Access
2 Citations
2,854 Views
22 Pages

Latent Space Perspicacity and Interpretation Enhancement (LS-PIE) Framework

  • Jesse Stevens,
  • Daniel N. Wilke and
  • Isaac I. Setshedi

25 September 2024

Linear latent variable models such as principal component analysis (PCA), independent component analysis (ICA), canonical correlation analysis (CCA), and factor analysis (FA) identify latent directions (or loadings) either ordered or unordered. These...

(This article belongs to the Special Issue Current Problems and Advances in Computational and Applied Mechanics (AfriComp6))
  • Article
  • Open Access
2 Citations
2,589 Views
18 Pages

Investigating the Potential of Latent Space for the Classification of Paint Defects

  • Doaa Almhaithawi,
  • Alessandro Bellini,
  • Georgios C. Chasparis and
  • Tania Cerquitelli

24 January 2025

Defect detection methods have greatly assisted human operators in various fields, from textiles to surfaces and mechanical components, by facilitating decision-making processes and reducing visual fatigue. This area of research is widely recognized a...

(This article belongs to the Section AI in Imaging)
  • Article
  • Open Access
3,612 Views
21 Pages

Toward Unbiased High-Quality Portraits through Latent-Space Evaluation

  • Doaa Almhaithawi,
  • Alessandro Bellini and
  • Tania Cerquitelli

Images, texts, voices, and signals can be synthesized by latent spaces in a multidimensional vector, which can be explored without the hurdles of noise or other interfering factors. In this paper, we present a practical use case that demonstrates the...

(This article belongs to the Topic Applications in Image Analysis and Pattern Recognition)
  • Article
  • Open Access
7 Citations
3,901 Views
23 Pages

Improving Deep Learning for Maritime Remote Sensing through Data Augmentation and Latent Space

  • Daniel Sobien,
  • Erik Higgins,
  • Justin Krometis,
  • Justin Kauffman and
  • Laura Freeman

Training deep learning models requires having the right data for the problem and understanding both your data and the models’ performance on that data. Training deep learning models is difficult when data are limited, so in this paper, we seek...

  • Article
  • Open Access
1 Citations
2,437 Views
25 Pages

Dual Space Latent Representation Learning for Image Representation

  • Yulei Huang,
  • Ziping Ma,
  • Huirong Li and
  • Jingyu Wang

31 May 2023

Semi-supervised non-negative matrix factorization (NMF) has achieved successful results due to the significant ability of image recognition by a small quantity of labeled information. However, there still exist problems to be solved such as the inter...

(This article belongs to the Section E1: Mathematics and Computer Science)
  • Feature Paper
  • Article
  • Open Access
8 Citations
3,163 Views
17 Pages

Latent-Space Dynamics for Prediction and Fault Detection in Geothermal Power Plant Operations

  • Yingxiang Liu,
  • Wei Ling,
  • Robert Young,
  • Jalal Zia and ,
  • Trenton T. Cladouhos and
  • Behnam Jafarpour
  • + 1 author+ 0 author

31 March 2022

This paper presents a latent-space dynamic neural network (LSDNN) model for the multi-step-ahead prediction and fault detection of a geothermal power plant’s operation. The model was trained to learn the dynamics of the power generation process...

(This article belongs to the Special Issue Machine Learning Applications in Petroleum Industries and Geothermal Systems)
  • Article
  • Open Access
5 Citations
3,673 Views
15 Pages

ADSAttack: An Adversarial Attack Algorithm via Searching Adversarial Distribution in Latent Space

  • Haobo Wang,
  • Chenxi Zhu,
  • Yangjie Cao,
  • Yan Zhuang and ,
  • Jie Li and
  • Xianfu Chen
  • + 1 author+ 0 author

Deep neural networks are susceptible to interference from deliberately crafted noise, which can lead to incorrect classification results. Existing approaches make less use of latent space information and conduct pixel-domain modification in the input...

(This article belongs to the Special Issue Advanced Techniques in Computing and Security)
  • Article
  • Open Access
5 Citations
4,905 Views
17 Pages

This article aims to provide an overview of the potential advantages and utilities of the recently proposed Latent Space Item Response Model (LSIRM) in the context of intelligence studies. The LSIRM integrates the traditional Rasch IRT model for psyc...

  • Article
  • Open Access
1 Citations
916 Views
24 Pages

26 May 2026

Large Language Models (LLMs) are typically safety-aligned using high-resource language data, but it remains unclear whether these constraints transfer reliably across distinct linguistic manifolds. This study examines the mathematical foundations of...

(This article belongs to the Special Issue Mathematical Foundations in NLP: Applications and Challenges)
  • Article
  • Open Access
879 Views
22 Pages

A Video Frame Prediction Method Based on Latent-Space Autoregressive Modeling

  • Congcong Zhang,
  • Jin Tian,
  • Lihua Gong,
  • Yujin Zhang and ,
  • Fei Wu and
  • Han Pan
  • + 1 author+ 0 author

1 May 2026

Video prediction is a fundamental task in computer vision with broad applications in intelligent robotics, autonomous driving, and related fields. However, existing methods often struggle to simultaneously model long-term temporal dependencies, prese...

(This article belongs to the Topic Intelligent Image Processing Technology)
  • Article
  • Open Access
563 Views
23 Pages

Research on Latent Space Convolution Filtering Algorithm for Water Hammer Signal

  • Kunchao Li,
  • Bing Hou,
  • Zhiwei Zhai,
  • Xiaowei Yan and
  • Zhenfeng Zhao

1 June 2026

Fracture diagnosis with water hammer pressure data is an important technology for petroleum exploration and development. Efficient filtering of acquired pressure data is a critical process to enhance diagnostic accuracy. The water hammer pressure mon...

  • Article
  • Open Access
322 Views
24 Pages

19 September 2026

Estimating multiscale ocean-surface states from sparse observations is challenging because the state is high-dimensional, sampling is irregular, and posterior distributions can be strongly non-Gaussian. We develop Latent-LWETKF, a structured latent-s...

  • Article
  • Open Access
1,111 Views
14 Pages

Aging State Classification of Lithium-Ion Batteries in a Low-Dimensional Latent Space

  • Limei Jin,
  • Franz Philipp Bereck,
  • Rüdiger-A. Eichel,
  • Josef Granwehr and
  • Christoph Scheurer

Battery datasets, whether gathered experimentally or through simulation, are typically high-dimensional and complex, which complicates the direct interpretation of degradation behavior or anomaly detection. To overcome these limitations, this study i...

  • Article
  • Open Access
16 Citations
3,282 Views
13 Pages

9 October 2021

It is of utmost importance to develop a computational method for accurate prediction of antioxidants, as they play a vital role in the prevention of several diseases caused by oxidative stress. In this correspondence, we present an effective computat...

(This article belongs to the Section Bioinformatics and Systems Biology)
  • Article
  • Open Access
17 Citations
4,971 Views
23 Pages

18 November 2022

Electroencephalography (EEG) signals can be analyzed in the temporal, spatial, or frequency domains. Noise and artifacts during the data acquisition phase contaminate these signals adding difficulties in their analysis. Techniques such as Independent...

(This article belongs to the Special Issue Advances in Explainable Artificial Intelligence (XAI))
  • Article
  • Open Access
1 Citations
619 Views
16 Pages

Cone-beam computed tomography (CBCT) is widely used in image-guided radiotherapy because of its low radiation dose and on-board acquisition capability. However, CBCT images often suffer from scatter artifacts, increased noise, reduced soft-tissue con...

(This article belongs to the Special Issue Intelligent Approaches for Solving Software Problems with AI Techniques, 2nd Edition)
  • Article
  • Open Access
2,365 Views
19 Pages

Controllable Unsupervised Snow Synthesis by Latent Style Space Manipulation

  • Hanting Yang,
  • Alexander Carballo,
  • Yuxiao Zhang and
  • Kazuya Takeda

12 October 2023

In the field of intelligent vehicle technology, there is a high dependence on images captured under challenging conditions to develop robust perception algorithms. However, acquiring these images can be both time-consuming and dangerous. To address t...

(This article belongs to the Topic Information Sensing Technology for Intelligent/Driverless Vehicle, 2nd Edition)
  • Article
  • Open Access
1 Citations
1,236 Views
18 Pages

8 May 2025

Hybrid evolutionary approaches have gained significant attention for solving complex optimization problems, but their potential for optimizing the low-dimensional latent space of generative adversarial networks (GANs) remains underexplored. This pape...

  • Article
  • Open Access
303 Views
41 Pages

AEGIS: Real-Time Latent-Space Backdoor Detection for Dependable and Secure Small Language Model Inference

  • Jamal Boussouf,
  • Ismail Lamaakal,
  • Ibrahim Ouahbi,
  • Khalid El Makkaoui and ,
  • Mounia Zaydi and
  • Belhassen Zouari
  • + 1 author+ 0 author

Backdoor attacks pose a serious threat to small language models (SLMs) because compromised models can behave normally on benign inputs while producing attacker-specified outputs when a hidden trigger is activated. Existing defenses commonly require m...

(This article belongs to the Special Issue Cybersecurity in AI-Driven Systems: Challenges and Innovations)
  • Article
  • Open Access
1 Citations
2,373 Views
20 Pages

17 December 2024

(1) Background: In recent years, the application of Transformers and Vision Transformers (ViTs) in medical image registration has been constrained by sliding attention mechanisms, which struggle to effectively capture non-adjacent but critical struct...

(This article belongs to the Special Issue Application of Machine Learning in Graphics and Images, 2nd Edition)
  • Article
  • Open Access
3 Citations
2,308 Views
35 Pages

Over the last three decades, architecture has undergone a sustained digital transformation that has progressively displaced the ontology of the geometric generator, understood here as the primary artefact through which form is produced, controlled, a...

(This article belongs to the Special Issue Architecture in the Digital Age)
  • Article
  • Open Access
1,584 Views
23 Pages

With the growing accessibility of tools such as online surveys and web scraping, longitudinal social network data are more commonly collected in social science research along with non-network survey data. Such data play a critical role in helping soc...

(This article belongs to the Special Issue Applications of Machine Learning and Data Science Methods in Social Sciences)
  • Article
  • Open Access
8 Citations
3,298 Views
15 Pages

Towards Sustainable Material Design: A Comparative Analysis of Latent Space Representations in AI Models

  • Ulises Martin Casado,
  • Facundo Ignacio Altuna and
  • Luis Alejandro Miccio

5 December 2024

In this study, we employed machine learning techniques to improve sustainable materials design by examining how various latent space representations affect the AI performance in property predictions. We compared three fingerprinting methodologies: (a...

  • Article
  • Open Access
1 Citations
1,272 Views
24 Pages

23 May 2025

Deep learning approaches based on autoencoders have been widely used for structural monitoring. Traditional approaches of autoencoders based on reconstruction errors involve limitations, since they do not exploit their hierarchical nature, and only h...

(This article belongs to the Special Issue Nondestructive Evaluation and Intelligent Monitoring for Composite Materials)
  • Article
  • Open Access
2 Citations
3,365 Views
23 Pages

There recently have been many studies examining conditional dependence between response accuracy and response times in cognitive tests. While most previous research has focused on revealing a general pattern of conditional dependence for all responde...

(This article belongs to the Topic Psychometric Methods: Theory and Practice)
  • Article
  • Open Access
11 Citations
3,234 Views
11 Pages

Multi-Perspective Feature Extraction and Fusion Based on Deep Latent Space for Diagnosis of Alzheimer’s Diseases

  • Libin Gao,
  • Zhongyi Hu,
  • Rui Li,
  • Xingjin Lu and ,
  • Zuoyong Li,
  • Xiabin Zhang and
  • Shiwei Xu
  • + 2 authors+ 0 author

5 October 2022

Resting-state functional magnetic resonance imaging (rs-fMRI) has been used to construct functional connectivity (FC) in the brain for the diagnosis and analysis of brain disease. Current studies typically use the Pearson correlation coefficient to c...

(This article belongs to the Section Computational Neuroscience, Neuroinformatics, and Neurocomputing)
  • Article
  • Open Access
9 Citations
4,388 Views
21 Pages

Impartially Validated Multiple Deep-Chain Models to Detect COVID-19 in Chest X-ray Using Latent Space Radiomics

  • Bardia Yousefi,
  • Satoru Kawakita,
  • Arya Amini,
  • Hamed Akbari and ,
  • Shailesh M. Advani,
  • Moulay Akhloufi,
  • Xavier P. V. Maldague and
  • Samad Ahadian
  • + 3 authors+ 0 author

14 July 2021

The COVID-19 pandemic continues to spread globally at a rapid pace, and its rapid detection remains a challenge due to its rapid infectivity and limited testing availability. One of the simply available imaging modalities in clinical routine involves...

(This article belongs to the Section Nuclear Medicine & Radiology)
  • Article
  • Open Access
1 Citations
3,393 Views
14 Pages

Continuous Latent Spaces Sampling for Graph Autoencoder

  • Zhongyu Li,
  • Geng Zhao,
  • Hao Ning,
  • Xin Jin and
  • Haoyang Yu

26 May 2023

This paper proposes colaGAE, a self-supervised learning framework for graph-structured data. While graph autoencoders (GAEs) commonly use graph reconstruction as a pretext task, this simple approach often yields poor model performance. To address thi...

  • Article
  • Open Access
9 Citations
2,899 Views
20 Pages

Different Ventricular Fibrillation Types in Low-Dimensional Latent Spaces

  • Carlos Paúl Bernal Oñate,
  • Francisco-Manuel Melgarejo Meseguer,
  • Enrique V. Carrera,
  • Juan José Sánchez Muñoz and ,
  • Arcadi García Alberola and
  • José Luis Rojo Álvarez
  • + 1 author+ 0 author

24 February 2023

The causes of ventricular fibrillation (VF) are not yet elucidated, and it has been proposed that different mechanisms might exist. Moreover, conventional analysis methods do not seem to provide time or frequency domain features that allow for recogn...

(This article belongs to the Section Biomedical Sensors)
  • Article
  • Open Access
1 Citations
2,306 Views
21 Pages

Image editing technology has brought about revolutionary changes in the field of architectural design, garnering significant attention in both the computer and architectural industries. However, architectural image editing is a challenging task due t...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
20 Citations
5,142 Views
14 Pages

24 October 2024

Machine learning generative models have opened up a new perspective for automated machine diagnostics. These methods improve decision-making by extracting features, classifying, and creating new observations using deep neural networks. Generative mod...

(This article belongs to the Special Issue Sensing and Machine Learning Control: Progress and Applications)
  • Article
  • Open Access
9 Citations
4,701 Views
18 Pages

11 January 2022

Hyperspectral imaging has increasingly been used in high-throughput plant phenotyping systems. Rapid advancement in the field of phenotyping has resulted in a wide array of hyperspectral imaging systems. However, sharing the plant feature prediction...

  • Article
  • Open Access
2 Citations
6,160 Views
17 Pages

Denoising Diffusion Models on Model-Based Latent Space

  • Carmelo Scribano,
  • Danilo Pezzi,
  • Giorgia Franchini and
  • Marco Prato

28 October 2023

With the recent advancements in the field of diffusion generative models, it has been shown that defining the generative process in the latent space of a powerful pretrained autoencoder can offer substantial advantages. This approach, by abstracting...

(This article belongs to the Special Issue Algorithms for Image Processing and Machine Vision)
  • Article
  • Open Access
8 Citations
2,674 Views
16 Pages

Latent Space Representation of Human Movement: Assessing the Effects of Fatigue

  • Thomas Rousseau,
  • Gentiane Venture and
  • Vincent Hernandez

4 December 2024

Fatigue plays a critical role in sports science, significantly affecting recovery, training effectiveness, and overall athletic performance. Understanding and predicting fatigue is essential to optimize training, prevent overtraining, and minimize th...

(This article belongs to the Special Issue Human Activity Recognition Using Sensors and Machine Learning: 2nd Edition)
  • Article
  • Open Access
20 Citations
4,091 Views
22 Pages

Dynamic Network Analysis of COVID-19 with a Latent Pandemic Space Model

  • Amanda M. Y. Chu,
  • Thomas W. C. Chan,
  • Mike K. P. So and
  • Wing-Keung Wong

In this paper, we propose a latent pandemic space modeling approach for analyzing coronavirus disease 2019 (COVID-19) pandemic data. We developed a pandemic space concept that locates different regions so that their connections can be quantified acco...

(This article belongs to the Section Digital Health)
  • Article
  • Open Access
57 Citations
14,054 Views
19 Pages

Image Anomaly Detection Using Normal Data Only by Latent Space Resampling

  • Lu Wang,
  • Dongkai Zhang,
  • Jiahao Guo and
  • Yuexing Han

3 December 2020

Detecting image anomalies automatically in industrial scenarios can improve economic efficiency, but the scarcity of anomalous samples increases the challenge of the task. Recently, autoencoder has been widely used in image anomaly detection without...

(This article belongs to the Special Issue New Industry 4.0 Advances in Industrial IoT and Visual Computing for Manufacturing Processes: Volume III)
  • Article
  • Open Access
5 Citations
3,320 Views
16 Pages

26 September 2022

The photo-sketch matching problem is challenging because the modality gap between a photo and a sketch is very large. This work features a novel approach to the use of an intermediate latent space between the two modalities that circumvents the probl...

(This article belongs to the Special Issue Challenges in Energy Perspective on Mobile Sensor Networks)
  • Article
  • Open Access
11 Citations
6,065 Views
16 Pages

Representing Deep Neural Networks Latent Space Geometries with Graphs

  • Carlos Lassance,
  • Vincent Gripon and
  • Antonio Ortega

27 January 2021

Deep Learning (DL) has attracted a lot of attention for its ability to reach state-of-the-art performance in many machine learning tasks. The core principle of DL methods consists of training composite architectures in an end-to-end fashion, where in...

(This article belongs to the Special Issue Efficient Graph Algorithms in Machine Learning)
  • Article
  • Open Access
144 Citations
13,877 Views
17 Pages

30 October 2018

Chemical autoencoders are attractive models as they combine chemical space navigation with possibilities for de novo molecule generation in areas of interest. This enables them to produce focused chemical libraries around a single lead compound for e...

(This article belongs to the Special Issue Machine Learning for Molecular Modelling in Drug Design)
  • Article
  • Open Access
1 Citations
1,374 Views
21 Pages

8 September 2025

Due to the increasing harmfulness of software vulnerabilities, it is increasingly suggested to propose more efficient vulnerability assessment methods. However, existing methods mainly rely on manual updates and inefficient rule matching, and they st...

(This article belongs to the Topic Addressing Security Issues Related to Modern Software)
  • Article
  • Open Access
1 Citations
2,172 Views
18 Pages

17 July 2025

Many radar applications rely primarily on visual classification for their evaluations. However, new research is integrating textual descriptions alongside visual input and showing that such multimodal fusion improves contextual understanding. A criti...

(This article belongs to the Special Issue AI-Powered RF Sensing and Signal Intelligence: Advances in Detection and Classification Techniques)
  • Article
  • Open Access
4 Citations
4,048 Views
13 Pages

Depth estimation plays a pivotal role in advancing human–robot interactions, especially in indoor environments where accurate 3D scene reconstruction is essential for tasks like navigation and object handling. Monocular depth estimation, which...

(This article belongs to the Section Bioinspired Sensorics, Information Processing and Control)
  • Article
  • Open Access
2 Citations
6,677 Views
11 Pages

Beyond Spectrograms: Rethinking Audio Classification from EnCodec’s Latent Space

  • Jorge Perianez-Pascual,
  • Juan D. Gutiérrez,
  • Laura Escobar-Encinas,
  • Álvaro Rubio-Largo and
  • Roberto Rodriguez-Echeverria

16 February 2025

This paper presents a novel approach to audio classification leveraging the latent representation generated by Meta’s EnCodec neural audio codec. We hypothesize that the compressed latent space representation captures essential audio features m...

(This article belongs to the Special Issue Artificial Intelligence Algorithms for Prediction, Control, Classification, Regression, and Intelligent Signal Processing in Industry)
  • Feature Paper
  • Article
  • Open Access
15 Citations
4,734 Views
16 Pages

From Hotel Reviews to City Similarities: A Unified Latent-Space Model

  • Luca Cagliero,
  • Moreno La Quatra and
  • Daniele Apiletti

A large portion of user-generated content published on the Web consists of opinions and reviews on products, services, and places in textual form. Many travellers and tourists routinely rely on such content to drive their choices, shaping trips and v...

(This article belongs to the Special Issue Big Data Analytics for Smart Cities)
  • Article
  • Open Access
3 Citations
2,578 Views
12 Pages

22 August 2024

A variational heteroencoder based on recurrent neural networks, trained with SMILES linear notations of molecular structures, was used to derive the following atomic descriptors: delta latent space vectors (DLSVs) obtained from the original SMILES of...

(This article belongs to the Section Computational and Theoretical Chemistry)
  • Article
  • Open Access
162 Views
25 Pages

Latent-Space Modeling Reveals Transcriptional Strategy Divergence in Flax Root Drought Response

  • Lili Guo,
  • Gongfu Shi,
  • Yao Wang,
  • Rui Xie and ,
  • Shuli Wei,
  • Xinhui Huang,
  • Huimin Shi,
  • Jing Fang,
  • Ying Liu and
  • Xiaoqing Zhao
  • + 6 authors+ 1 author

9 November 2026

Drought stress severely constrains flax (Linum usitatissimum L.) production, yet the transcriptional logic underlying genotypic variation in root drought tolerance remains unclear. We subjected 20 flax cultivars to drought at peak flowering, construc...

(This article belongs to the Section Plant Response to Abiotic Stress and Climate Change)
  • Article
  • Open Access
673 Views
22 Pages

1 May 2026

Synthetic Aperture Radar (SAR) images are affected by speckle noise, which limits their application in fine object interpretation and quantitative analysis. Recent deep learning-based single-image SAR despeckling methods have made significant progres...

(This article belongs to the Special Issue Advancing Synthetic Aperture Radar: Imaging, Processing, and Applications in Remote Sensing)
  • Article
  • Open Access
17 Citations
9,514 Views
24 Pages

31 December 2024

This article explores the practical implementation of autoencoders for anomaly detection, emphasizing their latent space manipulation and applicability across various domains. This study highlights the impact of optimizing parameter configurations, l...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
2 Citations
2,443 Views
14 Pages

Latent Space Representations for Marker-Less Realtime Hand–Eye Calibration

  • Juan Camilo Martínez-Franco,
  • Ariel Rojas-Álvarez,
  • Alejandra Tabares,
  • David Álvarez-Martínez and
  • César Augusto Marín-Moreno

18 July 2024

Marker-less hand–eye calibration permits the acquisition of an accurate transformation between an optical sensor and a robot in unstructured environments. Single monocular cameras, despite their low cost and modest computation requirements, pre...

(This article belongs to the Section Sensors and Robotics)
  • Article
  • Open Access
8 Citations
4,629 Views
17 Pages

17 January 2023

Auxiliary clinical diagnosis has been researched to solve unevenly and insufficiently distributed clinical resources. However, auxiliary diagnosis is still dominated by human physicians, and how to make intelligent systems more involved in the diagno...

(This article belongs to the Section Biomedical Sensors)

of 24