Skip to Content

971 Results Found

  • Article
  • Open Access
17 Citations
4,701 Views
15 Pages

Towards Efficient Federated Learning: Layer-Wise Pruning-Quantization Scheme and Coding Design

  • Zheqi Zhu,
  • Yuchen Shi,
  • Gangtao Xin,
  • Chenghui Peng and ,
  • Pingyi Fan and
  • Khaled B. Letaief
  • + 1 author+ 0 author

14 August 2023

As a promising distributed learning paradigm, federated learning (FL) faces the challenge of communication–computation bottlenecks in practical deployments. In this work, we mainly focus on the pruning, quantization, and coding of FL. By adopti...

(This article belongs to the Special Issue Information Theory for Distributed Systems)
  • Article
  • Open Access
189 Views
17 Pages

13 October 2026

Federated learning enables multiple clients to collaboratively train a global model without sharing raw data, but it is vulnerable to Byzantine attacks, in which malicious clients upload manipulated model updates to disrupt training or degrade model...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
548 Views
18 Pages

27 April 2026

Fine-tuning pre-trained encoder-based language models for down-stream tasks is typically performed by exploiting the output of the last encoder layer. However, an alternative line of research suggests that leveraging representations from multiple enc...

(This article belongs to the Special Issue The Advanced Trends in Natural Language Processing)
  • Article
  • Open Access
2 Citations
2,378 Views
21 Pages

On-Machine LTS Integration for Layer-Wise Surface Quality Characterization in MEX/P

  • Alejandro Fernández,
  • Pablo Zapico,
  • David Blanco,
  • Fernando Peña and ,
  • Natalia Beltrán and
  • Sabino Mateos
  • + 1 author+ 0 author

27 May 2024

Material Extrusion (MEX) currently stands as the most widespread Additive Manufacturing (AM) process, but part quality deficiencies remain a barrier to its generalized industrial adoption. Quality control in MEX is a complex task as extrusion perform...

(This article belongs to the Section Physical Sensors)
  • Article
  • Open Access
2 Citations
3,280 Views
16 Pages

20 April 2021

A deep-learning technology for knowledge transfer is necessary to advance and optimize efficient knowledge distillation. Here, we aim to develop a new adversarial optimization-based knowledge transfer method involved with a layer-wise dense flow that...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
16 Citations
4,458 Views
27 Pages

A Layer-Wise Strategy for Indoor As-Built Modeling Using Point Clouds

  • Lei Xie,
  • Ruisheng Wang,
  • Zutao Ming and
  • Dong Chen

19 July 2019

The automatic modeling of as-built building interiors, known as indoor building reconstruction, is gaining increasing attention because of its widespread applications. With the development of sensors to acquire high-quality point clouds, a new modeli...

(This article belongs to the Special Issue LiDAR and Time-of-flight Imaging)
  • Article
  • Open Access
8 Citations
4,461 Views
21 Pages

16 May 2021

Convolutional neural networks (CNNs) have achieved significant breakthroughs in various domains, such as natural language processing (NLP), and computer vision. However, performance improvement is often accompanied by large model size and computation...

(This article belongs to the Section Intelligent Sensors)
  • Article
  • Open Access
306 Views
34 Pages

28 August 2026

Transformer layers can develop distinct attention routing patterns during training, but how architectural access to structural information shapes this organization remains unclear. Existing structure-aware methods make this difficult to determine by...

(This article belongs to the Special Issue Machine Learning and Reasoning for Reliable and Explainable AI—2nd Edition)
  • Article
  • Open Access
18 Citations
6,360 Views
25 Pages

17 January 2019

Irregular spatial dependency is one of the major characteristics of remote sensing images, which brings about challenges for classification tasks. Deep supervised models such as convolutional neural networks (CNNs) have shown great capacity for remot...

(This article belongs to the Special Issue Pattern Analysis and Recognition in Remote Sensing)
  • Article
  • Open Access
664 Views
18 Pages

16 March 2026

As artificial intelligence (AI) systems are increasingly deployed in real-world applications, concerns regarding the unauthorized use of copyrighted images during model training have become more pronounced. In particular, both generative and discrimi...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
70 Citations
13,665 Views
20 Pages

23 December 2021

Trust and credibility in machine learning models are bolstered by the ability of a model to explain its decisions. While explainability of deep learning models is a well-known challenge, a further challenge is clarity of the explanation itself for re...

(This article belongs to the Special Issue Explainable Artificial Intelligence (XAI))
  • Article
  • Open Access
1 Citations
462 Views
37 Pages

A fully coupled three-dimensional (3D) thermo-magneto-elastic layer-wise formulation is developed for the analysis of multilayered flat and curved panels used in aerospace and aeronautical applications. The model relies on a system of coupled second-...

(This article belongs to the Special Issue Feature Papers in Journal of Composites Science in 2026)
  • Article
  • Open Access
2 Citations
853 Views
18 Pages

22 February 2026

Deep graph clustering aims to discover community structures in attributed graphs without labels and is useful for downstream applications such as citation analysis. However, existing methods often cannot make full use of both node features and graph...

  • Article
  • Open Access
11 Citations
4,191 Views
27 Pages

21 December 2022

Recent studies have proven that synthetic aperture radar (SAR) automatic target recognition (ATR) models based on deep neural networks (DNN) are vulnerable to adversarial examples. However, existing attacks easily fail in the case where adversarial p...

(This article belongs to the Special Issue Adversarial Attacks and Defenses for Remote Sensing Data)
  • Article
  • Open Access
1 Citations
1,687 Views
38 Pages

Tongan Speech Recognition Based on Layer-Wise Fine-Tuning Transfer Learning and Lexicon Parameter Enhancement

  • Junhao Geng,
  • Dongyao Jia,
  • Ziqi Li,
  • Zihao He and ,
  • Nengkai Wu,
  • Weijia Zhang and
  • Rongtao Cui
  • + 2 authors+ 0 author

24 October 2025

Speech recognition, as a key driver of artificial intelligence and global communication, has advanced rapidly in major languages, while studies on low-resource languages remain limited. Tongan, a representative Polynesian language, carries significan...

(This article belongs to the Special Issue Techniques and Applications of Natural Language Processing)
  • Article
  • Open Access
37 Citations
5,091 Views
41 Pages

Four Transformer-Based Deep Learning Classifiers Embedded with an Attention U-Net-Based Lung Segmenter and Layer-Wise Relevance Propagation-Based Heatmaps for COVID-19 X-ray Scans

  • Siddharth Gupta,
  • Arun K. Dubey,
  • Rajesh Singh,
  • Mannudeep K. Kalra and ,
  • Ajith Abraham,
  • Vandana Kumari,
  • John R. Laird,
  • Mustafa Al-Maini,
  • Neha Gupta and
  • Jasjit S. Suri
  • + 8 authors+ 3 authors

Background: Diagnosing lung diseases accurately is crucial for proper treatment. Convolutional neural networks (CNNs) have advanced medical image processing, but challenges remain in their accurate explainability and reliability. This study combines...

(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
  • Article
  • Open Access
9 Citations
4,493 Views
12 Pages

3 October 2022

Federated Learning is a widely adopted method for training neural networks over distributed data. One main limitation is the performance degradation that occurs when data are heterogeneously distributed. While many studies have attempted to address t...

(This article belongs to the Special Issue Federated and Transfer Learning Applications)
  • Article
  • Open Access
3 Citations
3,673 Views
22 Pages

G-protein-coupled receptors (GPCRs) are cell membrane proteins of relevance as therapeutic targets, and are associated to the development of treatments for illnesses such as diabetes, Alzheimer’s, or even cancer. Therefore, comprehending the un...

(This article belongs to the Special Issue New Applications in the Diagnosis and Therapy of Diseases)
  • Article
  • Open Access
19 Citations
7,126 Views
12 Pages

28 January 2023

Recent advances with large-scale pre-trained language models (e.g., BERT) have brought significant potential to natural language processing. However, the large model size hinders their use in IoT and edge devices. Several studies have utilized task-s...

(This article belongs to the Special Issue Data Engineering in the Internet of Things)
  • Article
  • Open Access
12 Citations
3,555 Views
17 Pages

Layer-Wise Discontinuous Galerkin Methods for Piezoelectric Laminates

  • Ivano Benedetti,
  • Vincenzo Gulizzi and
  • Alberto Milazzo

2 December 2020

In this work, a novel high-order formulation for multilayered piezoelectric plates based on the combination of variable-order interior penalty discontinuous Galerkin methods and general layer-wise plate theories is presented, implemented and tested....

(This article belongs to the Special Issue Feature Papers of Modelling)
  • Article
  • Open Access
7 Citations
4,295 Views
20 Pages

27 December 2021

Recurrent Neural Networks (RNNs) have been widely applied in various fields. However, in real-world application, because most devices like mobile phones are limited to the storage capacity when processing real-time information, an over-parameterized...

  • Article
  • Open Access
828 Views
25 Pages

Framework and Layer-Wise Word-Line Activation Method Design for CIM

  • Wei-Kai Cheng,
  • Shin-Yi Pai and
  • Shih-Hsu Huang

7 November 2025

Convolutional Neural Networks (CNNs) have excellent performance in various fields, such as machine learning, computer vision, and image recognition. With the development of CNNs, huge quantities of data in computing and transmission have placed signi...

(This article belongs to the Section Circuit and Signal Processing)
  • Article
  • Open Access
898 Views
22 Pages

Efficient Layer-Wise Cross-View Calibration and Aggregation for Multispectral Object Detection

  • Xiao He,
  • Tong Yang,
  • Tingzhou Yan,
  • Hongtao Li and ,
  • Yang Ge,
  • Zhijun Ren,
  • Zhe Liu,
  • Jiahe Jiang and
  • Chang Tang
  • + 4 authors+ 0 author

Multispectral object detection is a fundamental task with an extensive range of practical implications. In particular, combining visible (RGB) and infrared (IR) images can offer complementary information that enhances detection performance in differe...

(This article belongs to the Special Issue Multi-View Learning and Applications)
  • Article
  • Open Access
1,570 Views
16 Pages

Explainable Schizophrenia Classification from rs-fMRI Using SwiFT and TransLRP

  • Julian Weaver,
  • Emerald Zhang,
  • Nihita Sarma,
  • Alaa Melek and
  • Edward Castillo

4 November 2025

Schizophrenia is challenging to identify from resting-state functional MRI (rs-fMRI) due to subtle, distributed changes and the clinical need for transparent models. We build on the Swin 4D fMRI Transformer (SwiFT) to classify schizophrenia vs. contr...

(This article belongs to the Special Issue Machine Learning Techniques for Brain Data Analysis Using EEG, EMG or Image Data)
  • Letter
  • Open Access
14 Citations
4,806 Views
7 Pages

Effect of Layer-Wise Varying Parameters on the Microstructure and Soundness of Selective Laser Melted INCONEL 718 Alloy

  • Xiang Wang,
  • Jinwu Kang,
  • Tianjiao Wang,
  • Pengyue Wu and ,
  • Tao Feng and
  • Lele Zheng
  • + 1 author+ 0 author

5 July 2019

Selective laser melting (SLM) is a promising powder bed fusion additive manufacturing technique for metal part fabrication. In this paper, varying scanning speed in the range of 500 mm/s to 1900 mm/s, and laser power in the range of 100 W to 200 W, w...

(This article belongs to the Collection Additive Manufacturing: Alloy Design and Process Innovations)
  • Article
  • Open Access
1,065 Views
19 Pages

Layer-Wise Persistent Entropy of CT Scan Point Clouds for Lung Tumor Classification

  • C. Jeeva Jose,
  • Aneesh P. Baiju,
  • Riya Roy,
  • A. Harikrishnan and ,
  • Rahul Sanju,
  • P. B. Vinod Kumar,
  • K. K. Sherly,
  • Rinku Jacob and
  • G. Sreekumar
  • + 4 authors+ 0 author

In this study, a layer-wise point cloud representation of CT scan images is proposed, from which persistence diagrams are constructed and persistent entropy is computed as a compact topological feature for three-class lung tumor classification. Two p...

(This article belongs to the Topic Mathematical Applications and Computational Intelligence in Medicine and Biology)
  • Article
  • Open Access
10 Citations
5,083 Views
16 Pages

24 February 2023

Recently, the layer-wise N:M fine-grained sparse neural network algorithm (i.e., every M-weights contains N non-zero values) has attracted tremendous attention, as it can effectively reduce the computational complexity with negligible accuracy loss....

(This article belongs to the Special Issue Beyond Moore’s Law: Hardware Specialization and Advanced System on Chip)
  • Feature Paper
  • Article
  • Open Access
87 Citations
7,957 Views
34 Pages

An Equivalent Layer-Wise Approach for the Free Vibration Analysis of Thick and Thin Laminated and Sandwich Shells

  • Francesco Tornabene,
  • Nicholas Fantuzzi,
  • Michele Bacciocchi and
  • Junuthula N. Reddy

22 December 2016

The main purpose of the paper is to present an innovative higher-order structural theory to accurately evaluate the natural frequencies of laminated composite shells. A new kinematic model is developed starting from the theoretical framework given by...

(This article belongs to the Special Issue Applications of Generalized Differential and Integral Quadrature Methods)
  • Article
  • Open Access
5 Citations
2,877 Views
26 Pages

31 October 2022

The effect of adhesive layers bonding to the core of functionally graded (FG) surface layers is investigated using the free vibration of a five-layer sandwich composite plate resting on a Winkler elastic foundation in a thermal environment. It is ass...

(This article belongs to the Special Issue Multifunctional Composites, Volume II)
  • Article
  • Open Access
3 Citations
2,846 Views
13 Pages

Scrap steel inspection is a critical entry point for connecting the smelting process to the industrial internet, with its security and privacy being of vital importance. Current advancements in scrap steel inspection involve collecting scattered data...

(This article belongs to the Special Issue Network Security Management in Heterogeneous Networks)
  • Article
  • Open Access
408 Views
16 Pages

A Longitudinal Layer-Wise Strategy for Fabricating Tapered Micro-Cones by Ion-Beam Etching

  • Jingyu Huang,
  • Chenhui Deng,
  • Pengfei Wang,
  • Bohua Yin and ,
  • Liping Zhang and
  • Li Han
  • + 1 author+ 0 author

The controllable fabrication of tapered three-dimensional (3D) microstructures by ion-beam processing remains challenging, especially when both profile fidelity and geometric controllability are required. Tapered conical microstructures are of intere...

  • Article
  • Open Access
1 Citations
509 Views
18 Pages

9 June 2026

Laser powder bed fusion (L-PBF) has emerged as a core metal additive manufacturing technology for high-end sectors, including aerospace and medical device manufacturing. However, melting anomalies that occur during fabrication accumulate layer by lay...

(This article belongs to the Special Issue AI-Driven Modeling and Monitoring Towards Advanced Additive Manufacturing)
  • Article
  • Open Access
780 Views
22 Pages

Addressing Data Scarcity in Additive Manufacturing Monitoring via Synthetic Data Generation and Meta Pseudo-Labeling for Foundational Layer-Wise Segmentation

  • Yie Sheng Chen,
  • Petro Mushidi Tshakwanda,
  • Henok Berhanu Tsegaye,
  • Jin Zhang and ,
  • Harsh Kumar and
  • Michael Devetsikiotis
  • + 1 author+ 0 author

Additive manufacturing (AM) monitoring is fundamentally constrained by the severe scarcity of annotated data for layer-wise segmentation. This paper addresses this bottleneck by introducing a scalable, high-fidelity synthetic data generation pipeline...

(This article belongs to the Special Issue AI in Additive Manufacturing)
  • Article
  • Open Access
21 Citations
7,581 Views
20 Pages

In the development of aircraft comfort, one of the main issues is the sound transmission analysis to estimate the insulation capability of aeronautical panels. In this work, a higher-order shell finite element is proposed for the passive noise insula...

  • Article
  • Open Access
5 Citations
3,863 Views
19 Pages

29 March 2021

Recent studies have applied the superior performance of deep learning to mobile devices, and these studies have enabled the running of the deep learning model on a mobile device with limited computing power. However, there is performance degradation...

(This article belongs to the Special Issue Recent Trends in Embedded Technologies and Wearable Systems: Artificial Intelligence Solutions)
  • Article
  • Open Access
5 Citations
1,882 Views
28 Pages

Cognitively Inspired Federated Learning Framework for Interpretable and Privacy-Secured EEG Biomarker Prediction of Depression Relapse

  • Sana Yasin,
  • Umar Draz,
  • Tariq Ali,
  • Mohammad Hijji and ,
  • Muhammad Ayaz,
  • El-Hadi M. Aggoune and
  • Isha Yasin
  • + 2 authors+ 0 author

Depression relapse is a common issue during long-term care. We introduce a privacy-aware explainable personalized federated learning (PFL) framework that incorporates layer-wise relevance propagation and Shapley value analysis to provide patient-spec...

(This article belongs to the Special Issue Machine Learning and Deep Learning Applications in Healthcare, 2nd Edition)
  • Article
  • Open Access
40 Citations
6,606 Views
20 Pages

28 January 2021

Deep neural networks have evolved significantly in the past decades and are now able to achieve better progression of sensor data. Nonetheless, most of the deep models verify the ruling maxim in deep learning—bigger is better—so they have...

(This article belongs to the Section Intelligent Sensors)
  • Article
  • Open Access
8 Citations
2,749 Views
26 Pages

23 October 2020

The strong and weak formulations of a mixed layer-wise (LW) higher-order shear deformation theory (HSDT) are developed for the static analysis of functionally graded (FG) beams under various boundary conditions subjected to thermo-mechanical loads. T...

(This article belongs to the Special Issue Feature Papers in Journal of Composites Science in 2020)
  • Article
  • Open Access
2 Citations
2,284 Views
23 Pages

23 July 2025

Recent deep learning models, including GPT-4, have achieved remarkable performance using the back-propagation (BP) algorithm. However, the mechanism of BP is fundamentally different from how the human brain processes learning. To address this discrep...

  • Article
  • Open Access
175 Views
20 Pages

20 October 2026

Noise arising from physical and environmental factors can degrade the accuracy of image analysis. This study proposes a spiking neural network (SNN)-based image denoising model that combines ResNet18-based feature extraction with LIF-based spike proc...

(This article belongs to the Special Issue AI-Driven Image and Signal Processing)
  • Article
  • Open Access
11 Citations
3,801 Views
30 Pages

DeB3RTa: A Transformer-Based Model for the Portuguese Financial Domain

  • Higo Pires,
  • Leonardo Paucar and
  • Joao Paulo Carvalho

The complex and specialized terminology of financial language in Portuguese-speaking markets create significant challenges for natural language processing (NLP) applications, which must capture nuanced linguistic and contextual information to support...

  • Article
  • Open Access
90 Views
30 Pages

From Classification to Clinical Trust: 3D Deep Learning and Layer-Wise Explainability for Brain Tumor MRI

  • Nikolaos Pagonis,
  • Konstantinos Plomaritis,
  • Evangelos Kogias,
  • Nikolaos Foroglou and
  • Ioanna Chouvarda

5 November 2026

Preoperative differentiation of glioma from meningioma on MRI is important for treatment planning but depends on expert interpretation. A 3D ResNet-34 with CBAM attention was trained on four-modality MRI from 2251 BraTS 2023 patients (1801 for four-f...

(This article belongs to the Special Issue Medical Imaging: Artificial Intelligence, Image Recognition, and Machine Learning Techniques (2nd Edition))
  • Article
  • Open Access
503 Views
28 Pages

21 September 2026

Approximate multipliers have potential to improve energy efficiency in Deep Neural Networks but introduce computational errors that degrade accuracy. This paper introduces a novel method, leveraging approximate multipliers to enhance accuracy, while...

  • Article
  • Open Access
11 Citations
3,646 Views
38 Pages

5 January 2022

This paper presents the steady-state stress analysis of single-layered and multilayered plates and shells embedding Functionally Graded Material (FGM) layers under moisture conditions. This solution relies on an exact layer-wise approach; the formula...

(This article belongs to the Special Issue Recent Advances in Theoretical and Computational Modeling of Composite Materials and Structures)
  • Review
  • Open Access
31 Citations
7,032 Views
23 Pages

A Survey on Layer-Wise Security Attacks in IoT: Attacks, Countermeasures, and Open-Issues

  • Gaurav Sharma,
  • Stilianos Vidalis,
  • Niharika Anand,
  • Catherine Menon and
  • Somesh Kumar

28 September 2021

Security is a mandatory issue in any network, where sensitive data are transferred safely in the required direction. Wireless sensor networks (WSNs) are the networks formed in hostile areas for different applications. Whatever the application, the WS...

(This article belongs to the Special Issue Ambient Intelligence in IoT Environments)
  • Article
  • Open Access
16 Citations
3,250 Views
27 Pages

A mixed layer-wise (LW) higher-order shear deformation theory (HSDT) is developed for the thermal buckling analysis of simply-supported, functionally graded (FG) beams subjected to a uniform temperature change. The material properties of the FG beam...

(This article belongs to the Special Issue Feature Papers in Journal of Composites Science in 2021)
  • Article
  • Open Access
28 Citations
5,833 Views
20 Pages

16 July 2025

Human Activity Recognition (HAR) using wearable sensor data is increasingly important in healthcare, rehabilitation, and smart monitoring. This study systematically compared three dynamic neural network architectures—Finite Impulse Response Neu...

(This article belongs to the Special Issue Human Activity Recognition Using Sensors and Machine Learning: 2nd Edition)
  • Article
  • Open Access
18 Citations
6,021 Views
22 Pages

Development of AI-Based Diagnostic Model for the Prediction of Hydrate in Gas Pipeline

  • Youngjin Seo,
  • Byoungjun Kim,
  • Joonwhoan Lee and
  • Youngsoo Lee

20 April 2021

For the stable supply of oil and gas resources, industry is pushing for various attempts and technology development to produce not only existing land fields but also deep-sea, where production is difficult. The development of flow assurance technolog...

(This article belongs to the Section D1: Advanced Energy Materials)
  • Article
  • Open Access
7 Citations
3,723 Views
13 Pages

Isolating the Unique and Generic Movement Characteristics of Highly Trained Runners

  • Fabian Hoitz,
  • Laura Fraeulin,
  • Vinzenz von Tscharner,
  • Daniela Ohlendorf and ,
  • Benno M. Nigg and
  • Christian Maurer-Grubinger
  • + 1 author+ 0 author

28 October 2021

Human movement patterns were shown to be as unique to individuals as their fingerprints. However, some movement characteristics are more important than other characteristics for machine learning algorithms to distinguish between individuals. Here, we...

(This article belongs to the Section Intelligent Sensors)
  • Article
  • Open Access
32 Citations
8,828 Views
15 Pages

CNN-LRP: Understanding Convolutional Neural Networks Performance for Target Recognition in SAR Images

  • Bo Zang,
  • Linlin Ding,
  • Zhenpeng Feng,
  • Mingzhe Zhu and ,
  • Tao Lei,
  • Mengdao Xing and
  • Xianda Zhou
  • + 2 authors+ 0 author

1 July 2021

Target recognition is one of the most challenging tasks in synthetic aperture radar (SAR) image processing since it is highly affected by a series of pre-processing techniques which usually require sophisticated manipulation for different data and co...

(This article belongs to the Section Remote Sensors)

of 20