Skip to Content

4,469 Results Found

  • Feature Paper
  • Article
  • Open Access
38 Citations
4,942 Views
17 Pages

This work deals with the computationally-efficient inversion of microwave scattering data for brain stroke detection and monitoring. The proposed multi-step approach is based on the Learning-by-Examples (LBE) paradigm and naturally matches the stages...

(This article belongs to the Special Issue New Trends and Future Challenges in Computational Microwave Imaging)
  • Article
  • Open Access
791 Views
21 Pages

The Role of Worked Examples in Supporting Early Math Learning

  • Taylor Stone,
  • Lesenia R. Fish,
  • Nadia Chernyak,
  • Gabriella Guadalupe and
  • Sara Cordes

Worked examples—step-by-step examples of how to solve a problem correctly or incorrectly—are known to promote algebraic thinking in middle and high school students. Whether they are useful in facilitating math learning in much younger stu...

(This article belongs to the Special Issue Math Development and Cognitive Skills)
  • Article
  • Open Access
21 Citations
6,501 Views
15 Pages

Drug Target Identification with Machine Learning: How to Choose Negative Examples

  • Matthieu Najm,
  • Chloé-Agathe Azencott,
  • Benoit Playe and
  • Véronique Stoven

Identification of the protein targets of hit molecules is essential in the drug discovery process. Target prediction with machine learning algorithms can help accelerate this search, limiting the number of required experiments. However, Drug-Target I...

(This article belongs to the Special Issue Artificial Intelligence & Deep Learning Approaches for Structural Bioinformatics)
  • Article
  • Open Access
29 Citations
11,227 Views
10 Pages

Enhancing the Security of Deep Learning Steganography via Adversarial Examples

  • Yueyun Shang,
  • Shunzhi Jiang,
  • Dengpan Ye and
  • Jiaqing Huang

28 August 2020

Steganography is a collection of techniques for concealing the existence of information by embedding it within a cover. With the development of deep learning, some novel steganography methods have appeared based on the autoencoder or generative adver...

(This article belongs to the Special Issue Computing Methods in Steganography and Multimedia Security)
  • Article
  • Open Access
2,518 Views
15 Pages

1 August 2024

This paper explores how the Jesuit missionary Alfonso Vagnone selected, interpreted, and presented historical examples in The Western Learning of Governance (Zhiping xixue 治平西学) to support their political theories and view...

(This article belongs to the Special Issue The Catholic Encounter with Chinese Thought, Society and Politics in the Ming–Qing Dynasties)
  • Article
  • Open Access
7 Citations
2,986 Views
17 Pages

26 November 2021

With the upgrade of hardware and the consumer experience, the application of high-standard digital art technology to produce finished products is the current trend of digital entertainment visual development, through the application of next-generatio...

  • Article
  • Open Access
1 Citations
1,726 Views
25 Pages

10 April 2026

This study aims to examine the improvement of algebra problem-solving ability and metacognitive awareness among junior high school students through the use of visualization based on a deep learning approach. The research employed a quantitative metho...

(This article belongs to the Special Issue Teacher Emotion, Pedagogical Agents and Psychological Well-Being: Implications for Student Development)
  • Article
  • Open Access
24 Citations
6,843 Views
12 Pages

7 June 2022

Federated learning, a data privacy-focused distributed learning method, trains a model by aggregating local knowledge from clients. Each client collects and utilizes its own local dataset to train a local model. Local models in the connected federate...

(This article belongs to the Special Issue Advances in Intelligent Systems)
  • Article
  • Open Access
7 Citations
4,298 Views
21 Pages

Prototype-Based Support Example Miner and Triplet Loss for Deep Metric Learning

  • Shan Yang,
  • Yongfei Zhang,
  • Qinghua Zhao,
  • Yanglin Pu and
  • Hangyuan Yang

Deep metric learning aims to learn a mapping function that projects input data into a high-dimensional embedding space, facilitating the clustering of similar data points while ensuring dissimilar ones are far apart. The most recent studies focus on...

(This article belongs to the Special Issue Machine Intelligent Information and Efficient System)
  • Proceeding Paper
  • Open Access
2,166 Views
4 Pages

CALE: Learning by Example in Mathematics with Applets in Mathematical Computational Packages

  • Luis Martínez,
  • Javier Gutiérrez,
  • Leire Legarreta,
  • Iker Malaina and
  • Iraide Mardones

28 October 2018

In this work we present a methodology of “learning by example” assisted by computers in the study of mathematics. We propose the use of mathematical computational packages to program applets aimed to solve mathematical problems. Each time the student...

(This article belongs to the Proceedings of The 2nd Innovative and Creative Education and Teaching International Conference)
  • Article
  • Open Access
1,273 Views
22 Pages

Physically Active Learning (PAL) integrates physical activity into classroom teaching and has been shown to benefit students’ cognitive, social, and academic outcomes. Despite these advantages, PAL is not yet sustainably implemented in everyday...

  • Article
  • Open Access
2 Citations
2,169 Views
24 Pages

16 August 2025

Synthetic aperture radar (SAR) image classification under limited data conditions faces two major challenges: inter-class similarity, where distinct radar targets (e.g., tanks and armored trucks) have nearly identical scattering characteristics, and...

(This article belongs to the Special Issue Artificial Intelligence Algorithms for Prediction, Control, Classification, Regression, and Intelligent Signal Processing in Industry)
  • Article
  • Open Access
9 Citations
6,518 Views
31 Pages

17 April 2025

Research has advocated for the use of incorrect worked examples targeting specific conceptual barriers to enhance learning. From the perspective of cognitive load theory, we examined the relationship between instructional efficiency (correct and inco...

  • Article
  • Open Access
8 Citations
3,944 Views
17 Pages

9 November 2022

Recently, artificial intelligence (AI) based on IoT sensors has been widely used, which has increased the risk of attacks targeting AI. Adversarial examples are among the most serious types of attacks in which the attacker designs inputs that can cau...

(This article belongs to the Section Intelligent Sensors)
  • Review
  • Open Access
390 Citations
29,212 Views
22 Pages

What Is Machine Learning, Artificial Neural Networks and Deep Learning?—Examples of Practical Applications in Medicine

  • Jakub Kufel,
  • Katarzyna Bargieł-Łączek,
  • Szymon Kocot,
  • Maciej Koźlik and ,
  • Wiktoria Bartnikowska,
  • Michał Janik,
  • Łukasz Czogalik,
  • Piotr Dudek,
  • Mikołaj Magiera and
  • Katarzyna Gruszczyńska
  • + 9 authors+ 4 authors

Machine learning (ML), artificial neural networks (ANNs), and deep learning (DL) are all topics that fall under the heading of artificial intelligence (AI) and have gained popularity in recent years. ML involves the application of algorithms to autom...

(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
  • Article
  • Open Access
3 Citations
2,964 Views
12 Pages

The self-management principle holds that higher learning performance is obtained when learners actively use instructional strategies to manage the working memory load imposed by a learning task. Self-management studies with spatially separated but mu...

(This article belongs to the Special Issue Cognitive Load Theory: Emerging Trends and Innovations)
  • Article
  • Open Access
9 Citations
3,460 Views
19 Pages

24 April 2023

Calls for more integrated approaches to STEM have reached every sector of education, including formal and nonformal spaces, from early childhood to tertiary levels. The goal of STEM education as an integrated effort shifts beyond acquiring knowledge...

(This article belongs to the Special Issue STEM Education: Current Trends, Perspectives, and Narratives)
  • Article
  • Open Access
22 Citations
4,137 Views
19 Pages

Towards Figurative Expression Enhancement: Effects of the SVVR-Supported Worked Example Approach on the Descriptive Writing of Highly Engaged Students

  • Yi-Pin Huang,
  • Xiao-Li Zheng,
  • Chuang-Kai Chiu,
  • Jun Lei and ,
  • Gang Yang,
  • Hoisoo Kim and
  • Feng Wang
  • + 2 authors+ 0 author

6 November 2021

During the past decades, many researchers have attempted to explore effective teaching methods for developing students’ descriptive writing performance. In this study, the worked example was implemented as an effective way of guiding students to prov...

(This article belongs to the Special Issue Augmented Reality and Virtual Reality-supported Sustainable Education)
  • Article
  • Open Access
29 Citations
4,292 Views
15 Pages

17 November 2022

Researchers are focusing on the vulnerabilities of deep learning models for remote sensing; various attack methods have been proposed, including universal adversarial examples. Existing universal adversarial examples, however, are only designed to fo...

(This article belongs to the Special Issue Adversarial Attacks and Defenses for Remote Sensing Data)
  • Article
  • Open Access
3 Citations
2,093 Views
20 Pages

Security issues surrounding deep learning models weaken their application effectiveness in various fields. Studying attacks against deep learning models contributes to evaluating their security and improving it in a targeted manner. Among the methods...

(This article belongs to the Special Issue Novel Methods Applied to Security and Privacy Problems in Future Networking Technologies)
  • Article
  • Open Access
5 Citations
3,031 Views
40 Pages

13 November 2024

The proliferation of deep learning has transformed artificial intelligence, demonstrating prowess in domains such as image recognition, natural language processing, and robotics. Nonetheless, deep learning models are susceptible to adversarial exampl...

(This article belongs to the Special Issue Advances in Trustworthy and Robust Artificial Intelligence)
  • Article
  • Open Access
12 Citations
7,414 Views
13 Pages

Today, the main two security issues for deep learning are data poisoning and adversarial examples. Data poisoning consists of perverting a learning system by manipulating a small subset of the training data, while adversarial examples entail bypassin...

(This article belongs to the Section Data)
  • Article
  • Open Access
2 Citations
4,454 Views
21 Pages

9 December 2022

Automatic Speech Recognition (ASR) systems are ubiquitous in various commercial applications. These systems typically rely on machine learning techniques for transcribing voice commands into text for further processing. Despite their success in many...

(This article belongs to the Section Visualization and Computer Graphics)
  • Article
  • Open Access
32 Citations
8,510 Views
18 Pages

30 March 2023

SQL injection is a highly detrimental web attack technique that can result in significant data leakage and compromise system integrity. To counteract the harm caused by such attacks, researchers have devoted much attention to the examination of SQL i...

(This article belongs to the Section Cybersecurity)
  • Article
  • Open Access
17 Citations
4,408 Views
13 Pages

7 May 2021

One of the most intriguing phenomenons related to deep learning is the so-called adversarial examples. These samples are visually equivalent to normal inputs, undetectable for humans, yet they cause the networks to output wrong results. The phenomeno...

  • Article
  • Open Access
6 Citations
1,994 Views
16 Pages

In this study, we propose a novel method for generating untargeted adversarial examples using a Generative Adversarial Network (GAN) in an unrestricted black-box environment. The proposed approach produces adversarial examples that are classified int...

  • Article
  • Open Access
7 Citations
3,981 Views
15 Pages

A Hybrid Adversarial Attack for Different Application Scenarios

  • Xiaohu Du,
  • Jie Yu,
  • Zibo Yi,
  • Shasha Li and ,
  • Jun Ma,
  • Yusong Tan and
  • Qinbo Wu
  • + 2 authors+ 0 author

21 May 2020

Adversarial attack against natural language has been a hot topic in the field of artificial intelligence security in recent years. It is mainly to study the methods and implementation of generating adversarial examples. The purpose is to better deal...

(This article belongs to the Special Issue Natural Language Processing: Emerging Neural Approaches and Applications)
  • Article
  • Open Access
6 Citations
3,229 Views
15 Pages

20 September 2022

Deep neural networks (DNNs) have attracted extensive attention because of their excellent performance in many areas; however, DNNs are vulnerable to adversarial examples. In this paper, we propose a similarity metric called inner-class adjusted cosin...

(This article belongs to the Special Issue Human and Artificial Intelligence)
  • Article
  • Open Access
19 Citations
4,464 Views
15 Pages

6 March 2021

This paper presents research focusing on visualization and pattern recognition based on computer science. Although deep neural networks demonstrate satisfactory performance regarding image and voice recognition, as well as pattern analysis and intrus...

(This article belongs to the Section A: Computer Science)
  • Article
  • Open Access
2 Citations
4,087 Views
19 Pages

Detecting High-Resolution Adversarial Images with Few-Shot Deep Learning

  • Junjie Zhao,
  • Junfeng Wu,
  • James Msughter Adeke,
  • Sen Qiao and
  • Jinwei Wang

30 April 2023

Deep learning models have enabled significant performance improvements to remote sensing image processing. Usually, a large number of training samples is required for detection models. In this study, a dynamic simulation training strategy is designed...

(This article belongs to the Special Issue Semantic Segmentation of High-Resolution Images with Deep Learning, Volume II)
  • Article
  • Open Access
48 Citations
11,931 Views
18 Pages

29 March 2022

Adversarial attacks pose a major threat to machine learning and to the systems that rely on it. In the cybersecurity domain, adversarial cyber-attack examples capable of evading detection are especially concerning. Nonetheless, an example generated f...

(This article belongs to the Topic Cyber Security and Critical Infrastructures)
  • Article
  • Open Access
7 Citations
3,504 Views
17 Pages

A Novel Adversarial Detection Method for UAV Vision Systems via Attribution Maps

  • Zhun Zhang,
  • Qihe Liu,
  • Chunjiang Wu,
  • Shijie Zhou and
  • Zhangbao Yan

7 December 2023

With the rapid advancement of unmanned aerial vehicles (UAVs) and the Internet of Things (IoTs), UAV-assisted IoTs has become integral in areas such as wildlife monitoring, disaster surveillance, and search and rescue operations. However, recent stud...

(This article belongs to the Special Issue UAV-Assisted Internet of Things)
  • Article
  • Open Access
1 Citations
1,754 Views
25 Pages

8 July 2025

Generating adversarial examples under black-box settings poses significant challenges due to the inaccessibility of internal model information. This complexity is further exacerbated when attempting to achieve a balance between the attack success rat...

(This article belongs to the Section A: Computer Science)
  • Article
  • Open Access
6 Citations
6,082 Views
30 Pages

Detecting Adversarial Examples Using Surrogate Models

  • Borna Feldsar,
  • Rudolf Mayer and
  • Andreas Rauber

27 November 2023

Deep Learning has enabled significant progress towards more accurate predictions and is increasingly integrated into our everyday lives in real-world applications; this is true especially for Convolutional Neural Networks (CNNs) in the field of image...

(This article belongs to the Collection Extravaganza Feature Papers on Hot Topics in Machine Learning and Knowledge Extraction)
  • Article
  • Open Access
12 Citations
4,253 Views
24 Pages

Approaching Adversarial Example Classification with Chaos Theory

  • Anibal Pedraza,
  • Oscar Deniz and
  • Gloria Bueno

24 October 2020

Adversarial examples are one of the most intriguing topics in modern deep learning. Imperceptible perturbations to the input can fool robust models. In relation to this problem, attack and defense methods are being developed almost on a daily basis....

  • Article
  • Open Access
12 Citations
4,504 Views
17 Pages

13 February 2023

Deep learning-based vulnerability detection models have received widespread attention; however, these models are susceptible to adversarial attack, and adversarial examples are a primary research direction to improve the robustness of the models. The...

  • Article
  • Open Access
4 Citations
3,860 Views
22 Pages

Latent-Insensitive Autoencoders for Anomaly Detection

  • Muhammad S. Battikh and
  • Artem A. Lenskiy

30 December 2021

Reconstruction-based approaches to anomaly detection tend to fall short when applied to complex datasets with target classes that possess high inter-class variance. Similar to the idea of self-taught learning used in transfer learning, many domains a...

(This article belongs to the Section E: Applied Mathematics)
  • Article
  • Open Access
38 Citations
5,485 Views
27 Pages

Adversarial Self-Supervised Learning for Robust SAR Target Recognition

  • Yanjie Xu,
  • Hao Sun,
  • Jin Chen,
  • Lin Lei and ,
  • Kefeng Ji and
  • Gangyao Kuang
  • + 1 author+ 0 author

17 October 2021

Synthetic aperture radar (SAR) can perform observations at all times and has been widely used in the military field. Deep neural network (DNN)-based SAR target recognition models have achieved great success in recent years. Yet, the adversarial robus...

(This article belongs to the Special Issue Target Detection and Information Extraction in Radar Images)
  • Article
  • Open Access
23 Citations
10,124 Views
29 Pages

Adversarial Patch Attacks on Deep-Learning-Based Face Recognition Systems Using Generative Adversarial Networks

  • Ren-Hung Hwang,
  • Jia-You Lin,
  • Sun-Ying Hsieh,
  • Hsuan-Yu Lin and
  • Chia-Liang Lin

11 January 2023

Deep learning technology has developed rapidly in recent years and has been successfully applied in many fields, including face recognition. Face recognition is used in many scenarios nowadays, including security control systems, access control manag...

(This article belongs to the Special Issue Artificial Intelligence and Deep Learning in Sensors and Applications)
  • Article
  • Open Access
8 Citations
4,357 Views
15 Pages

Is Homomorphic Encryption-Based Deep Learning Secure Enough?

  • Jinmyeong Shin,
  • Seok-Hwan Choi and
  • Yoon-Ho Choi

24 November 2021

As the amount of data collected and analyzed by machine learning technology increases, data that can identify individuals is also being collected in large quantities. In particular, as deep learning technology—which requires a large amount of a...

(This article belongs to the Section Intelligent Sensors)
  • Article
  • Open Access
2,533 Views
17 Pages

27 April 2020

As a research field of symmetry journals, computer vision has received more and more attention. Person re-identification (re-ID) has become a research hotspot in computer vision. We focus on one-example person re-ID, where each person only has one la...

  • Article
  • Open Access
2 Citations
3,515 Views
23 Pages

The actual problem of adversarial attacks on classifiers, mainly implemented using deep neural networks, is considered. This problem is analyzed with a generalization to the case of any classifiers synthesized by machine learning methods. The imperfe...

(This article belongs to the Section Safety, Security, Privacy, and Cyber Resilience)
  • Article
  • Open Access
24 Citations
4,949 Views
19 Pages

Pointer Defect Detection Based on Transfer Learning and Improved Cascade-RCNN

  • Weidong Zhao,
  • Hancheng Huang,
  • Dan Li,
  • Feng Chen and
  • Wei Cheng

1 September 2020

To meet the practical needs of detecting various defects on the pointer surface and solve the difficulty of detecting some defects on the pointer surface, this paper proposes a transfer learning and improved Cascade-RCNN deep neural network (TICNET)...

(This article belongs to the Section Sensing and Imaging)
  • Article
  • Open Access
3 Citations
3,800 Views
24 Pages

14 September 2022

The 2020 Sustainability Index (SI), a benchmark system, shows that 2% of the 184 municipal water and wastewater utilities (WWS) in Sweden have a good performance level (green), i.e., they meet all benchmark requirements for the “climate adaptat...

(This article belongs to the Section Urban Water Management)
  • Article
  • Open Access
9 Citations
4,985 Views
18 Pages

You Only Attack Once: Single-Step DeepFool Algorithm

  • Jun Li,
  • Yanwei Xu,
  • Yaocun Hu,
  • Yongyong Ma and
  • Xin Yin

31 December 2024

Adversarial attacks expose the latent vulnerabilities within artificial intelligence systems, necessitating a reassessment and enhancement of model robustness to ensure the reliability and security of deep learning models against malicious attacks. W...

(This article belongs to the Special Issue Adversarial Attacks and Cyber Security: Trends and Challenges)
  • Article
  • Open Access
14 Citations
2,804 Views
25 Pages

19 February 2025

The rapid proliferation of ransomware variants necessitates more effective detection mechanisms, as traditional signature-based methods are increasingly inadequate. These conventional methods rely on manual feature extraction and matching, which are...

(This article belongs to the Section Networks)
  • Article
  • Open Access
1 Citations
4,263 Views
14 Pages

Automated Segmentation to Make Hidden Trigger Backdoor Attacks Robust against Deep Neural Networks

  • Saqib Ali,
  • Sana Ashraf,
  • Muhammad Sohaib Yousaf,
  • Shazia Riaz and
  • Guojun Wang

5 April 2023

The successful outcomes of deep learning (DL) algorithms in diverse fields have prompted researchers to consider backdoor attacks on DL models to defend them in practical applications. Adversarial examples could deceive a safety-critical system, whic...

(This article belongs to the Topic Machine and Deep Learning)
  • Article
  • Open Access
1 Citations
1,289 Views
13 Pages

A Controlled Variation Approach for Example-Based Explainable AI in Colorectal Polyp Classification

  • Miguel Filipe Fontes,
  • Alexandre Henrique Neto,
  • João Dallyson Almeida and
  • António Trigueiros Cunha

30 July 2025

Medical imaging is vital for diagnosing and treating colorectal cancer (CRC), a leading cause of mortality. Classifying colorectal polyps and CRC precursors remains challenging due to operator variability and expertise dependence. Deep learning (DL)...

(This article belongs to the Special Issue Innovative Applications of AI, Machine Learning, IoT, and Assistive Robots in Health Monitoring and Care)
  • Feature Paper
  • Article
  • Open Access
27 Citations
4,479 Views
13 Pages

Adversarial examples are theorized to exist for every type of neural network application. Adversarial examples have been proven to exist in neural networks for visual-spectrum applications and that they are highly transferable between such neural net...

(This article belongs to the Section Artificial Intelligence)
  • Proceeding Paper
  • Open Access
1,763 Views
5 Pages

Virtual Visits as a Learning Tool for Historical Heritage in Two Specific Examples: Évora and Mérida

  • Mario Corrales-Serrano,
  • Jesús Sánchez-Martín,
  • José Moreno-Losada and
  • Francisco Zamora-Polo

This paper presents an educational experience in the area of learning about Art History, in particular, about the Greco-Roman period, using an innovative resource that is available due to current technology: the virtual visit. This resource allows st...

(This article belongs to the Proceedings of The 5th Ibero-American Congress on Entrepreneurship, Energy, Environment and Technology - CIEEMAT 2019)

of 90