Skip to Content

76 Results Found

  • Article
  • Open Access
1 Citations
4,463 Views
26 Pages

26 May 2019

Machine learning techniques have shown superior predictive power, among which Bayesian network classifiers (BNCs) have remained of great interest due to its capacity to demonstrate complex dependence relationships. Most traditional BNCs tend to build...

(This article belongs to the Special Issue Information Theoretic Measures and Their Applications)
  • Article
  • Open Access
4 Citations
1,826 Views
21 Pages

26 November 2024

Windshear is a microscale meteorological phenomenon that can be dangerous to aircraft during the take-off and landing phases. Accurate windshear detection plays a significant role in air traffic control. In this paper, we aim to investigate a machine...

  • Article
  • Open Access
2 Citations
1,857 Views
20 Pages

An Accelerator for Semi-Supervised Classification with Granulation Selection

  • Yunsheng Song,
  • Jing Zhang,
  • Xinyue Zhao and
  • Jie Wang

Semi-supervised classification is one of the core methods to deal with incomplete tag information without manual intervention, which has been widely used in various real problems for its excellent performance. However, the existing algorithms need to...

(This article belongs to the Special Issue Advances in Intelligent Data Analysis and Its Applications)
  • Article
  • Open Access
2,020 Views
19 Pages

5 August 2023

Semi-supervised metric learning intends to learn a distance function from the limited labeled data as well as a large amount of unlabeled data to better gauge the similarities of any two instances than using a general distance function. However, most...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
1 Citations
3,274 Views
25 Pages

25 July 2019

To mitigate the negative effect of classification bias caused by overfitting, semi-naive Bayesian techniques seek to mine the implicit dependency relationships in unlabeled testing instances. By redefining some criteria from information theory, Targe...

(This article belongs to the Section Information Theory, Probability and Statistics)
  • Article
  • Open Access
8 Citations
2,978 Views
16 Pages

Motor power curves (MPCs) have received great attention for use in diagnosing the working conditions of sucker rod pumping systems (SRPSs) because of their advantages in accessibility and real-time performance. However, existing MPC-based approaches...

(This article belongs to the Special Issue Deep Learning and Machine Learning Mathematical Models for Computer Assisted Diagnostic Systems)
  • Article
  • Open Access
3 Citations
2,658 Views
22 Pages

30 November 2023

Human Activity Recognition (HAR) systems have made significant progress in recognizing and classifying human activities using sensor data from a variety of sensors. Nevertheless, they have struggled to automatically discover novel activity classes wi...

(This article belongs to the Special Issue Human Activity Recognition Using Sensors and Machine Learning)
  • Article
  • Open Access
5 Citations
3,031 Views
21 Pages

14 March 2025

To efficiently utilize limited resources, this paper proposes a semi-supervised object detection (SSOD) approach based on novel adaptive weighted active learning (AWAL) and orthogonal data augmentation (ODA). An uncertainty sampling framework is appl...

(This article belongs to the Section Intelligent Sensors)
  • Data Descriptor
  • Open Access
4 Citations
5,953 Views
25 Pages

A Probabilistic Bag-to-Class Approach to Multiple-Instance Learning

  • Kajsa Møllersen,
  • Jon Yngve Hardeberg and
  • Fred Godtliebsen

26 June 2020

Multi-instance (MI) learning is a branch of machine learning, where each object (bag) consists of multiple feature vectors (instances)—for example, an image consisting of multiple patches and their corresponding feature vectors. In MI classific...

(This article belongs to the Special Issue Machine Learning in Image Analysis and Pattern Recognition)
  • Article
  • Open Access
3 Citations
2,973 Views
19 Pages

An Object Detection Method Based on Feature Uncertainty Domain Adaptation for Autonomous Driving

  • Yuan Zhu,
  • Ruidong Xu,
  • Chongben Tao,
  • Hao An and ,
  • Zhipeng Sun and
  • Ke Lu
  • + 1 author+ 0 author

25 May 2023

The environment perception algorithm in autonomous driving is trained in the source domain, leading to domain drift and reduced detection accuracy in the target domain due to shifts in background feature distribution. To address this issue, a domain...

  • Article
  • Open Access
1 Citations
1,801 Views
20 Pages

18 April 2025

Few-shot object detection (FSOD) based on fine-tuning is essential for analyzing optical remote sensing images. However, existing methods mainly focus on natural images and overlook the scale variations in remote sensing images, leading to feature co...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
12 Citations
4,227 Views
23 Pages

In recent years, the informatization of the educational system has caused a substantial increase in educational data. Educational data mining can assist in identifying the factors influencing students’ performance. However, two challenges have...

(This article belongs to the Special Issue Future Trends and Challenges of Ubiquitous Computing and Smart Systems)
  • Article
  • Open Access
16 Citations
4,253 Views
16 Pages

10 November 2021

Traffic systems, where human and autonomous drivers interact, are a very relevant instance of complex systems and produce behaviors that can be regarded as trajectories over time. Their monitoring can be achieved by means of carefully stated properti...

(This article belongs to the Special Issue Focus on Traffic Safety: From Artificial Intelligence Approaches to Other Advances)
  • Article
  • Open Access

Ensemble Inductive Transfer Learning

  • Xiaobo Liu,
  • Guangjun Wang,
  • Zhihua Cai and
  • Harry Zhang

Inductive transfer learning is a major research area in transfer learning which aims at achieving a high performance in the target domain by inducing the useful knowledge from the source domain. By combining decisions from individual classifiers, ens...

  • Article
  • Open Access
2 Citations
1,946 Views
12 Pages

Deep learning (DL) systems have been remarkably successful in various applications, but they could have critical misbehaviors. To identify the weakness of a trained model and overcome it with new data collection(s), one needs to figure out the corner...

(This article belongs to the Special Issue Image/Video Processing and Encoding for Contemporary Applications)
  • Article
  • Open Access
4 Citations
3,924 Views
15 Pages

17 October 2019

In supervised Activities of Daily Living (ADL) recognition systems, annotating collected sensor readings is an essential, yet exhaustive, task. Readings are collected from activity-monitoring sensors in a 24/7 manner. The size of the produced dataset...

  • Article
  • Open Access
11 Citations
4,285 Views
16 Pages

10 March 2020

Power law describes a common behavior in which a few factors play decisive roles in one thing. Most software defects occur in very few instances. In this study, we proposed a novel approach that adopts power law function characteristics for software...

  • Article
  • Open Access
4 Citations
1,752 Views
21 Pages

4 May 2025

Cell nuclei instance segmentation plays a critical role in pathological image analysis. In recent years, fully supervised methods for cell nuclei instance segmentation have achieved significant results. However, in practical medical image processing,...

  • Article
  • Open Access
57 Views
20 Pages

We study learning-augmented combinatorial optimization in the absence of externally supplied labels. We propose CLIO (Contrastive Learning with Iterative Optimization), a search-guided graph neural framework for the maximum independent set (MIS) prob...

  • Article
  • Open Access
7 Citations
4,596 Views
26 Pages

Revisiting Consistency for Semi-Supervised Semantic Segmentation

  • Ivan Grubišić,
  • Marin Oršić and
  • Siniša Šegvić

13 January 2023

Semi-supervised learning is an attractive technique in practical deployments of deep models since it relaxes the dependence on labeled data. It is especially important in the scope of dense prediction because pixel-level annotation requires substanti...

(This article belongs to the Special Issue Artificial Intelligence and Deep Learning in Sensors and Applications)
  • Article
  • Open Access
4 Citations
1,045 Views
19 Pages

Reliable detection of previously unseen classes under distributional shift remains a central challenge in concept learning and explainable artificial intelligence. In particular, high-performance deep learning models often lack statistically grounded...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
7 Citations
6,976 Views
13 Pages

Knowledge Discovery in Spectral Data by Means of Complex Networks

  • Massimiliano Zanin,
  • David Papo,
  • José Luis González Solís,
  • Juan Carlos Martínez Espinosa and ,
  • Claudio Frausto-Reyes,
  • Pascual Palomares Anda,
  • Ricardo Sevilla-Escoboza,
  • Rider Jaimes-Reategui,
  • Stefano Boccaletti and
  • Pedro Sousa
  • + 6 authors+ 1 author

11 March 2013

In the last decade, complex networks have widely been applied to the study of many natural and man-made systems, and to the extraction of meaningful information from the interaction structures created by genes and proteins. Nevertheless, less attenti...

(This article belongs to the Special Issue Data Processing in Metabolomics)
  • Article
  • Open Access
2,643 Views
22 Pages

Semi-Supervised Building Detection from High-Resolution Remote Sensing Imagery

  • Daoyuan Zheng,
  • Jianing Kang,
  • Kaishun Wu,
  • Yuting Feng and ,
  • Han Guo,
  • Xiaoyun Zheng,
  • Shengwen Li and
  • Fang Fang
  • + 3 authors+ 0 author

1 August 2023

Urban building information reflects the status and trends of a region’s development and is essential for urban sustainability. Detection of buildings from high-resolution (HR) remote sensing images (RSIs) provides a practical approach for quick...

(This article belongs to the Section Sustainability in Geographic Science)
  • Article
  • Open Access
9 Citations
3,803 Views
24 Pages

Mixture-Based Probabilistic Graphical Models for the Label Ranking Problem

  • Enrique G. Rodrigo,
  • Juan C. Alfaro,
  • Juan A. Aledo and
  • José A. Gámez

31 March 2021

The goal of the Label Ranking (LR) problem is to learn preference models that predict the preferred ranking of class labels for a given unlabeled instance. Different well-known machine learning algorithms have been adapted to deal with the LR problem...

(This article belongs to the Special Issue Bayesian Inference in Probabilistic Graphical Models)
  • Article
  • Open Access
34 Citations
4,025 Views
18 Pages

Multi-Level Alignment Network for Cross-Domain Ship Detection

  • Chujie Xu,
  • Xiangtao Zheng and
  • Xiaoqiang Lu

16 May 2022

Ship detection is an important research topic in the field of remote sensing. Compared with optical detection methods, Synthetic Aperture Radar (SAR) ship detection can penetrate clouds to detect hidden ships in all-day and all-weather. Currently, th...

  • Article
  • Open Access
10 Citations
3,311 Views
32 Pages

26 March 2022

Despite the availability of a large amount of free unlabeled data, collecting sufficient training data for supervised learning models is challenging due to the time and cost involved in the labeling process. The active learning technique we present h...

(This article belongs to the Section E: Applied Mathematics)
  • Article
  • Open Access
203 Views
38 Pages

26 October 2026

Unmanned aerial vehicle (UAV) remote sensing provides an efficient approach for livestock monitoring in alpine grassland environments, particularly in regions where traditional field surveys are constrained by complex terrain and large spatial covera...

(This article belongs to the Special Issue Task-Oriented UAV Applications in Agro-Forestry and Livestock Systems)
  • Article
  • Open Access
15 Citations
3,384 Views
16 Pages

Active Mask-Box Scoring R-CNN for Sonar Image Instance Segmentation

  • Fangjin Xu,
  • Jianxing Huang,
  • Jie Wu and
  • Longyu Jiang

Instance segmentation of sonar images is an effective method for underwater target recognition. However, the mismatch among positioning accuracy found by boxIoU and classification confidence, which is used as NMS score in current instance segmentatio...

(This article belongs to the Section Bioelectronics)
  • Article
  • Open Access
1,141 Views
21 Pages

14 November 2025

Accurate uncertainty estimation in unlabeled data represents a fundamental challenge in active learning. Traditional deep active learning approaches suffer from a critical limitation: uncertainty-based selection strategies tend to concentrate excessi...

  • Article
  • Open Access
1,048 Views
20 Pages

Tri-Invariance Contrastive Framework for Robust Unsupervised Person Re-Identification

  • Lei Wang,
  • Chengang Liu,
  • Xiaoxiao Wang,
  • Weidong Gao and ,
  • Xuejian Ge and
  • Shunjie Zhu
  • + 1 author+ 0 author

6 November 2025

Unsupervised person re-identification (Re-ID) has been proven very effective and it boosts the performance in learning representations from unlabeled data in the dataset. Most current methods have good accuracy, but there are two main problems. First...

(This article belongs to the Special Issue Mathematical Computation for Pattern Recognition and Computer Vision)
  • Article
  • Open Access
32 Citations
4,430 Views
15 Pages

3 September 2022

Due to the cost of acquiring and labeling remote sensing images, only a limited number of images with the target objects are obtained and labeled in some practical applications, which severely limits the generalization capability of typical deep lear...

(This article belongs to the Special Issue AI Interpretation of Satellite, Aerial, Ground, and Underwater Image and Video Sequences)
  • Article
  • Open Access
592 Views
27 Pages

2 September 2026

In precision agriculture, object detection is often limited by the scarcity of image data, as agricultural data collection is inherently constrained by season, geographical location and crop growth cycles. Generative AI offers a practical way to expa...

(This article belongs to the Special Issue Enhancing Generalization in Agricultural AI: Bridging Data Gaps and Boosting Model Robustness)
  • Article
  • Open Access
1 Citations
2,792 Views
19 Pages

RiSSNet: Contrastive Learning Network with a Relaxed Identity Sampling Strategy for Remote Sensing Image Semantic Segmentation

  • Haifeng Li,
  • Wenxuan Jing,
  • Guo Wei,
  • Kai Wu and ,
  • Mingming Su,
  • Lu Liu,
  • Hao Wu,
  • Penglong Li and
  • Ji Qi
  • + 4 authors+ 0 author

6 July 2023

Contrastive learning techniques make it possible to pretrain a general model in a self-supervised paradigm using a large number of unlabeled remote sensing images. The core idea is to pull positive samples defined by data augmentation techniques clos...

(This article belongs to the Special Issue Geospatial Foundation Model in Urban Environments: Challenges and New Technologies)
  • Article
  • Open Access
1 Citations
2,518 Views
21 Pages

Locality Preserving Property Constrained Contrastive Learning for Object Classification in SAR Imagery

  • Jing Wang,
  • Sirui Tian,
  • Xiaolin Feng,
  • Bo Zhang and ,
  • Fan Wu,
  • Hong Zhang and
  • Chao Wang
  • + 2 authors+ 0 author

24 July 2023

Robust unsupervised feature learning is a critical yet tough task for synthetic aperture radar (SAR) automatic target recognition (ATR) with limited labeled data. The developing contrastive self-supervised learning (CSL) method, which learns informat...

(This article belongs to the Special Issue SAR-Based Signal Processing and Target Recognition)
  • Article
  • Open Access
8 Citations
4,551 Views
26 Pages

13 May 2019

Over recent decades, the rapid growth in data makes ever more urgent the quest for highly scalable Bayesian networks that have better classification performance and expressivity (that is, capacity to respectively describe dependence relationships bet...

(This article belongs to the Special Issue Bayesian Inference and Information Theory)
  • Article
  • Open Access
742 Views
44 Pages

Accelerating Active Learning for Image Classification Through FPGA-Based Implementation

  • Angelo Barbieri,
  • Christopher A. Flores,
  • Wladimir Valenzuela and
  • Francisco Saavedra

12 June 2026

Image sensors produce high-dimensional visual data for classification algorithms. Deep Neural Networks (DNNs) achieve high accuracy but require large labeled datasets and computational and energy resources, limiting their use in embedded systems. Act...

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

25 September 2026

Acoustic and image sensors in unattended ground sensor systems often operate at different sampling rates and use different trigger mechanisms and fields of view, so their observations are asynchronous and lack instance-level correspondence. In additi...

(This article belongs to the Special Issue Advanced Computer Vision Techniques: AI-Based Object Detection, Tracking, Surveillance and Security Applications)
  • Article
  • Open Access
9 Citations
3,055 Views
23 Pages

Unsupervised Feature Selection with Latent Relationship Penalty Term

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

21 December 2023

With the exponential growth of high dimensional unlabeled data, unsupervised feature selection (UFS) has attracted considerable attention due to its excellent performance in machine learning. Existing UFS methods implicitly assigned the same attribut...

  • Article
  • Open Access
3 Citations
2,946 Views
21 Pages

Study on the Influence of Chirality in the Threading of Calix[6]arene Hosts with Dialkylammonium Axles

  • Carmen Talotta,
  • Gerardo Concilio,
  • Paolo Della Sala,
  • Carmine Gaeta and ,
  • Christoph A. Schalley and
  • Placido Neri
  • + 1 author+ 0 author

15 November 2020

The influence of chirality in calixarene threading has been studied by exploiting the “superweak anion approach”. In particular, the formation of chiral pseudo[2]rotaxanes bearing a classical stereogenic center in their axle and/or wheel...

(This article belongs to the Special Issue Calixarene Complexes: Synthesis, Properties and Applications)
  • Article
  • Open Access
13 Citations
4,008 Views
15 Pages

11 January 2023

As one of the entropy-based methods, the k-Star algorithm benefits from information theory in computing the distances between data instances during the classification task. k-Star is a machine learning method with a high classification performance an...

(This article belongs to the Special Issue Information Theory for Data Science)
  • Article
  • Open Access
2 Citations
1,071 Views
18 Pages

Comparative Analysis of Self-Labeled Algorithms for Predicting MOOC Dropout: A Case Study

  • George Raftopoulos,
  • Georgios Kostopoulos,
  • Gregory Davrazos,
  • Theodor Panagiotakopoulos and ,
  • Sotiris Kotsiantis and
  • Achilles Kameas
  • + 1 author+ 0 author

12 November 2025

Massive Open Online Courses (MOOCs) have expanded global access to education but continue to struggle with high attrition rates. This study presents a comparative analysis of self-labeled Semi-Supervised Learning (SSL) algorithms for predicting learn...

(This article belongs to the Special Issue Advances in Intelligent Information Systems and AI Applications—2nd Edition)
  • Article
  • Open Access
7 Citations
3,215 Views
12 Pages

30 October 2022

Morphological and functional changes in retinal vessels are indicators of a variety of chronic diseases, such as diabetes, stroke, and hypertension. However, without a large number of high-quality annotations, existing deep learning-based medical ima...

(This article belongs to the Section Bioelectronics)
  • Article
  • Open Access
1 Citations
2,288 Views
14 Pages

24 October 2024

Student performance prediction is a critical research challenge in the field of educational data mining. To address this issue, various machine learning methods have been employed with significant success, including instance-based algorithms, decisio...

  • Article
  • Open Access
11 Citations
5,206 Views
18 Pages

Data Augmentation vs. Domain Adaptation—A Case Study in Human Activity Recognition

  • Evaggelos Spyrou,
  • Eirini Mathe,
  • Georgios Pikramenos,
  • Konstantinos Kechagias and
  • Phivos Mylonas

Recent advances in big data systems and databases have made it possible to gather raw unlabeled data at unprecedented rates. However, labeling such data constitutes a costly and timely process. This is especially true for video data, and in particula...

  • Proceeding Paper
  • Open Access
3 Citations
7,663 Views
27 Pages

The Details Matter: Preventing Class Collapse in Supervised Contrastive Learning

  • Daniel Y. Fu,
  • Mayee F. Chen,
  • Michael Zhang,
  • Kayvon Fatahalian and
  • Christopher Ré

Supervised contrastive learning optimizes a loss that pushes together embeddings of points from the same class while pulling apart embeddings of points from different classes. Class collapse—when every point from the same class has the same emb...

(This article belongs to the Proceedings of AAAI Workshop on Artificial Intelligence with Biased or Scarce Data (AIBSD))
  • Article
  • Open Access
1 Citations
1,037 Views
31 Pages

Spectroscopic Pulse Embeddings by Contrastive Learning from Unlabeled Data for Pile-Up Analysis

  • Congyu Lin,
  • Xiaoying Zheng,
  • Tom Trigano,
  • Dima Bykhovsky and ,
  • Yongxin Zhu and
  • Li Tian
  • + 1 author+ 0 author

30 March 2026

In nuclear spectroscopy, a physical phenomenon known as the pile-up effect distorts direct measurements by causing temporal overlap of detector pulses. Existing deep learning-based pile-up correction methods rely heavily on supervised training with s...

(This article belongs to the Section Sensors Development)
  • Article
  • Open Access
441 Views
29 Pages

5 September 2026

Supervised learning in fields such as genomics and medical imaging is often hindered by the high cost of expert data annotation. Active learning addresses this bottleneck by iteratively selecting the most informative unlabeled samples for labeling. H...

(This article belongs to the Special Issue Advances in Machine Learning, High-Dimensional Inference, Shrinkage Estimation, and Model Validation)
  • Review
  • Open Access
  • Best Paper Award
195 Citations
29,502 Views
38 Pages

6 February 2023

Despite the availability and ease of collecting a large amount of free, unlabeled data, the expensive and time-consuming labeling process is still an obstacle to labeling a sufficient amount of training data, which is essential for building supervise...

(This article belongs to the Section E: Applied Mathematics)
  • Article
  • Open Access
888 Views
25 Pages

Mitigating Class Imbalance and False-Negative Supervision in Remote Sensing Semantic Segmentation Using Object-Centric Patch Sampling

  • Yogesh Regmi,
  • Sandeep Gautam,
  • Gaurav Parajuli,
  • Abinash Silwal and ,
  • Roshan Bhandari and
  • Tri Dev Acharya
  • + 1 author+ 0 author

21 August 2026

In Deep Learning Remote Sensing, data quantity is rarely the limiting factor. A single high-resolution satellite image can yield thousands of training patches. What determines model performance, yet remains largely overlooked, is the quality of those...

(This article belongs to the Special Issue Remote Sensing Measurements of Land Use and Land Cover)
  • Article
  • Open Access
2 Citations
1,176 Views
22 Pages

Subclass-Aware Contrastive Semi-Supervised Learning for Inflammatory Bowel Disease Classification from Colonoscopy Images

  • Kechen Lin,
  • Guangcong Ruan,
  • Xiaoyang Zou,
  • Yongjian Nian and ,
  • Yanling Wei and
  • Guoyan Zheng
  • + 1 author+ 0 author

Inflammatory bowel disease (IBD) includes Crohn’s disease (CD) and ulcerative colitis (UC). The accurate classification of IBD from colonoscopy images is critical for diagnosis and treatment. However, the lack of labeled data poses a major chal...

(This article belongs to the Special Issue Advances in Computational Imaging and Artificial Intelligence for Biomedical and Clinical Applications)

of 2