Skip to Content

1,986 Results Found

  • Article
  • Open Access
1 Citations
3,075 Views
27 Pages

28 August 2021

Real-life data are bounded and heavy-tailed variables. Zero-one-inflated beta (ZOIB) regression is used for modelling them. There are no appropriate methods to address the problem of missing data in repeated bounded outcomes. We developed an imputati...

(This article belongs to the Special Issue Methods and Applications of Statistics in the Social and Health Sciences)
  • Article
  • Open Access
1 Citations
2,160 Views
23 Pages

9 May 2024

This paper presents an indirect adaptive neural network (NN) control algorithm tailored for flexible joint robots (FJRs), aimed at achieving desired transient and steady-state performance. To simplify the controller design process, the original highe...

(This article belongs to the Special Issue Research and Development of Intelligent Robot)
  • Feature Paper
  • Article
  • Open Access
391 Views
28 Pages

Risk-Adaptive Behavioral Attenuation via Episode-Latched Policy Gating and Bounded Relearning for Deployed Reinforcement Learning Agents

  • Mehdi Samieiyeganeh,
  • Tahir Mehmood,
  • Parisa Bahraminikoo,
  • Soobia Saeed and ,
  • Soubraylu Sivakumar and
  • Farhad Nadi
  • + 1 author+ 0 author

13 October 2026

Reinforcement learning behaviors can become harmful after deployment even when the policy is unchanged, a risk existing methods address mainly before or during training rather than through reversible correction. This paper proposes a risk-adaptive at...

  • Article
  • Open Access
40 Citations
5,980 Views
28 Pages

19 January 2021

Meta-learning, or “learning to learn”, refers to techniques that infer an inductive bias from data corresponding to multiple related tasks with the goal of improving the sample efficiency for new, previously unobserved, tasks. A key perfo...

(This article belongs to the Special Issue The Role of Signal Processing and Information Theory in Modern Machine Learning)
  • Article
  • Open Access
6 Citations
4,745 Views
16 Pages

AdaCB: An Adaptive Gradient Method with Convergence Range Bound of Learning Rate

  • Xuanzhi Liao,
  • Shahnorbanun Sahran,
  • Azizi Abdullah and
  • Syaimak Abdul Shukor

19 September 2022

Adaptive gradient descent methods such as Adam, RMSprop, and AdaGrad achieve great success in training deep learning models. These methods adaptively change the learning rates, resulting in a faster convergence speed. Recent studies have shown their...

(This article belongs to the Special Issue AI-Based Image Processing)
  • Feature Paper
  • Article
  • Open Access
2 Citations
3,123 Views
24 Pages

Data-Bound Adaptive Federated Learning: FedAdaDB

  • Fotios Zantalis and
  • Grigorios Koulouras

24 June 2025

Federated Learning (FL) enables decentralized Machine Learning (ML), focusing on preserving data privacy, but faces a unique set of optimization challenges, such as dealing with non-IID data, communication overhead, and client drift. Adaptive optimiz...

(This article belongs to the Special Issue IoT Meets AI: Driving the Next Generation of Technology)
  • Article
  • Open Access
1,524 Views
16 Pages

23 August 2023

Label corruption leads to a significant challenge in supervised learning, particularly in deep neural networks. This paper considers recovering a small corrupted subset of data samples which are typically caused by non-expert sources, such as automat...

(This article belongs to the Special Issue Advances in Artificial Intelligence: Data, Methods and Interdisciplinary Applications)
  • Feature Paper
  • Article
  • Open Access
13 Citations
3,590 Views
13 Pages

24 August 2022

We consider information-theoretic bounds on the expected generalization error for statistical learning problems in a network setting. In this setting, there are K nodes, each with its own independent dataset, and the models from the K nodes have to b...

(This article belongs to the Special Issue Information Theory and Machine Learning)
  • Article
  • Open Access
9 Citations
5,511 Views
29 Pages

30 July 2020

This paper studies the hybridization of Mixed Integer Programming (MIP) with dual heuristics and machine learning techniques, to provide dual bounds for a large scale optimization problem from an industrial application. The case study is the EURO/ROA...

  • Article
  • Open Access
52 Citations
10,743 Views
14 Pages

17 August 2018

Since remote sensing images are captured from the top of the target, such as from a satellite or plane platform, ship targets can be presented at any orientation. When detecting ship targets using horizontal bounding boxes, there will be background c...

(This article belongs to the Section Remote Sensors)
  • Communication
  • Open Access
5 Citations
3,730 Views
15 Pages

28 December 2022

In this paper, we derive the Cramér–Rao lower bounds (CRLB) for direction of arrival (DoA) estimation by using sparse Bayesian learning (SBL) and the Laplace prior. CRLB is a lower bound on the variance of the estimator, the change of CR...

(This article belongs to the Section Communications)
  • Article
  • Open Access
74 Views
25 Pages

11 November 2026

Analytical micromechanical schemes predict the effective stiffness of two-phase composites accurately and cheaply, yet they are opaque to the influence of individual descriptors, are not analytically invertible for target-driven design, and grow oner...

(This article belongs to the Section Composites Modelling and Characterization)
  • Article
  • Open Access
105 Views
22 Pages

14 November 2026

Small multirotor UAVs navigate with a single noisy GPS receiver while wind pushes the true airframe off its commanded track. We study a guidance architecture that keeps a short-horizon predicted reference and corrects it with every delayed measuremen...

  • Article
  • Open Access

19 November 2026

This study investigates the integration of reinforcement learning (RL) with Model Reference Adaptive Control (MRAC) to improve pitch-axis tracking of an aerial platform operating under nonlinear dynamics and external disturbances. A hybrid RL-MRAC fr...

(This article belongs to the Special Issue Reinforcement Learning in Dynamic Control and Robotic Autonomy)
  • Article
  • Open Access
4 Citations
2,380 Views
18 Pages

28 October 2025

Accurate angular alignment of wafers is essential in ion implantation to prevent channeling effects that degrade device performance. This study proposes a real-time notch-angle-detection system based on you only look once version 8 with oriented boun...

(This article belongs to the Special Issue Advances in Machine Learning and Data Mining: Emerging Trends and Applications)
  • Article
  • Open Access
399 Views
30 Pages

11 August 2026

Optimization plays a critical role in training deep neural networks, directly impacting convergence speed, model generalization, and stability. While existing methods such as stochastic gradient descent (SGD) and adaptive optimizers like Adam and Ada...

  • Article
  • Open Access
640 Views
42 Pages

26 June 2026

Gain-scheduled and cascaded proportional–integral–derivative (PID) autopilots remain common practical baselines for fixed-wing unmanned aerial vehicles (UAVs), but training one shared learned controller for heading, altitude, and true air...

(This article belongs to the Special Issue Mission Planning, Perception and Control for Drones in Wide-Area Operations)
  • Article
  • Open Access
33 Citations
4,746 Views
20 Pages

PAC-Bayes Unleashed: Generalisation Bounds with Unbounded Losses

  • Maxime Haddouche,
  • Benjamin Guedj,
  • Omar Rivasplata and
  • John Shawe-Taylor

12 October 2021

We present new PAC-Bayesian generalisation bounds for learning problems with unbounded loss functions. This extends the relevance and applicability of the PAC-Bayes learning framework, where most of the existing literature focuses on supervised learn...

(This article belongs to the Special Issue Approximate Bayesian Inference)
  • Article
  • Open Access
1 Citations
1,053 Views
32 Pages

2 December 2025

Distributed cloud networks spanning multiple jurisdictions face significant challenges in anomaly detection due to privacy constraints, regulatory requirements, and communication limitations. This paper presents a mathematically rigorous framework fo...

(This article belongs to the Section Computational Engineering)
  • Article
  • Open Access
1 Citations
1,296 Views
19 Pages

31 August 2025

AI-driven agricultural automation increasingly demands efficient data generation methods for training deep learning models in autonomous robotic systems. Traditional bounding box annotation methods for agricultural objects present significant challen...

(This article belongs to the Collection AI, Sensors and Robotics for Smart Agriculture)
  • Article
  • Open Access
283 Views
17 Pages

25 September 2026

This paper addresses the depth regulation of an inspection-class remotely operated vehicle whose hydrodynamic model is uncertain and whose environment applies a persistent, non-vanishing wave disturbance. A neural-network learning term added to a pro...

(This article belongs to the Section Ocean Engineering)
  • Article
  • Open Access
2 Citations
1,377 Views
17 Pages

17 September 2025

This paper investigates the attitude control problems of spacecraft subject to external disturbances and compound actuator faults, including both additive and multiplicative components. To address these problems, an improved learning observer (ILO) i...

(This article belongs to the Section Aerospace Actuators)
  • Article
  • Open Access
3,244 Views
14 Pages

This paper examines the computational feasibility of the standard model of learning in economic theory. It is shown that the information update technique at the heart of this model is impossible to compute in all but the simplest scenarios. Specifica...

  • Article
  • Open Access
8 Citations
3,486 Views
14 Pages

The branch-and-bound algorithm for combinatorial optimization typically relies on a plethora of handcraft expert heuristics, and a research direction, so-called learn-to-branch, proposes to replace the expert heuristics in branch-and-bound with machi...

(This article belongs to the Special Issue Analog AI Circuits and Systems)
  • Article
  • Open Access
4 Citations
2,041 Views
19 Pages

Study on Scheduling Problems with Learning Effects and Past Sequence Delivery Times

  • Hongyu He,
  • Yanzhi Zhao,
  • Xiaojun Ma,
  • Yuan-Yuan Lu and ,
  • Na Ren and
  • Ji-Bo Wang
  • + 1 author+ 0 author

30 September 2023

In this paper, we study a single-machine green scheduling problem with learning effects and past-sequence-dependent delivery times. The problem can be properly applied to tackle green manufacturing where production and delivery time are variable and...

(This article belongs to the Special Issue Optimization in Scheduling and Control Problems)
  • Article
  • Open Access
495 Views
25 Pages

1 September 2026

Data-driven prediction of crumb–rubber modified asphalt (CRMA) binder properties is usually reported on datasets in which a small number of mix-designs is swept across several test temperatures, so that the row count greatly exceeds the number...

(This article belongs to the Section Materials Simulation and Design)
  • Article
  • Open Access
472 Views
22 Pages

Optimal Configuration of Traction Power Supply Systems Based on Deep Reinforcement Learning

  • Ming Nie,
  • Kai Yuan,
  • Chongbo Sun,
  • Yi Song and ,
  • Yudi Ding and
  • Zhiwei Wan
  • + 1 author+ 0 author

To address the coupling among power supply topology, module selection, capacity allocation, and N-2 contingency assessment in flexible traction power supply systems, a deep-reinforcement-learning-guided branch-and-bound method is proposed for equipme...

(This article belongs to the Topic Collection Series on Applied System Innovation)
  • Article
  • Open Access
322 Views
21 Pages

16 September 2026

Nonsmooth gear-contact vibration under variable-speed operation is strongly affected by mesh-phase evolution, backlash-induced contact switching, and unilateral tooth contact. This study investigates local line-of-action vibration suppression in a si...

(This article belongs to the Section Automation and Control Systems)
  • Article
  • Open Access
24 Citations
4,995 Views
16 Pages

Cervical Cell/Clumps Detection in Cytology Images Using Transfer Learning

  • Chuanyun Xu,
  • Mengwei Li,
  • Gang Li,
  • Yang Zhang and ,
  • Chengjie Sun and
  • Nanlan Bai
  • + 1 author+ 0 author

13 October 2022

Cervical cancer is one of the most common and deadliest cancers among women and poses a serious health risk. Automated screening and diagnosis of cervical cancer will help improve the accuracy of cervical cell screening. In recent years, there have b...

(This article belongs to the Special Issue Imaging of Cervical Cancer)
  • Feature Paper
  • Article
  • Open Access
10 Citations
10,307 Views
17 Pages

15 November 2017

In recent years, tools from information theory have played an increasingly prevalent role in statistical machine learning. In addition to developing efficient, computationally feasible algorithms for analyzing complex datasets, it is of theoretical i...

(This article belongs to the Special Issue Information Theory in Machine Learning and Data Science)
  • Article
  • Open Access
3 Citations
3,679 Views
27 Pages

18 November 2021

When confronted with massive data streams, summarizing data with dimension reduction methods such as PCA raises theoretical and algorithmic pitfalls. A principal curve acts as a nonlinear generalization of PCA, and the present paper proposes a novel...

(This article belongs to the Special Issue Approximate Bayesian Inference)
  • Article
  • Open Access
4 Citations
2,815 Views
26 Pages

Adaptive filtering remains a cornerstone of modern signal processing but faces fundamental challenges when confronted with rapidly changing or nonlinear environments. This work investigates the integration of deep learning into adaptive-filter archit...

(This article belongs to the Special Issue Advanced System Architectures and AI-Driven Innovations for Next-Generation Computing)
  • Article
  • Open Access
3 Citations
4,766 Views
27 Pages

Reinforcement Learning in a New Keynesian Model

  • Szabolcs Deák,
  • Paul Levine,
  • Joseph Pearlman and
  • Bo Yang

31 May 2023

We construct a New Keynesian (NK) behavioural macroeconomic model with bounded-rationality (BR) and heterogeneous agents. We solve and simulate the model using a third-order approximation for a given policy and evaluate its properties using this solu...

(This article belongs to the Special Issue Advancements in Reinforcement Learning Algorithms)
  • Article
  • Open Access
5 Citations
2,348 Views
25 Pages

28 September 2023

We study the excess minimum risk in statistical inference, defined as the difference between the minimum expected loss when estimating a random variable from an observed feature vector and the minimum expected loss when estimating the same random var...

(This article belongs to the Special Issue Advances in Information and Coding Theory II)
  • Article
  • Open Access
83 Citations
10,498 Views
16 Pages

Automatic Building Extraction from Google Earth Images under Complex Backgrounds Based on Deep Instance Segmentation Network

  • Qi Wen,
  • Kaiyu Jiang,
  • Wei Wang,
  • Qingjie Liu and ,
  • Qing Guo,
  • Lingling Li and
  • Ping Wang
  • + 2 authors+ 0 author

15 January 2019

Building damage accounts for a high percentage of post-natural disaster assessment. Extracting buildings from optical remote sensing images is of great significance for natural disaster reduction and assessment. Traditional methods mainly are semi-au...

(This article belongs to the Special Issue Deep Learning Remote Sensing Data)
  • Article
  • Open Access
522 Views
33 Pages

The rapid growth of scientific spatiotemporal data poses increasing challenges for efficient storage and transmission while preserving sufficient reconstruction fidelity for downstream analysis. Existing compression methods remain limited in this set...

(This article belongs to the Special Issue Machine Learning: Techniques, Industry Applications, Code Sharing, and Future Trends)
  • Article
  • Open Access
5 Citations
3,975 Views
17 Pages

Self-Adaptive Deep Multiple Kernel Learning Based on Rademacher Complexity

  • Shengbing Ren,
  • Wangbo Shen,
  • Chaudry Naeem Siddique and
  • You Li

5 March 2019

The deep multiple kernel learning (DMKL) method has caused widespread concern due to its better results compared with shallow multiple kernel learning. However, existing DMKL methods, which have a fixed number of layers and fixed type of kernels, hav...

  • Article
  • Open Access
7 Citations
3,698 Views
19 Pages

On Stability of Perturbed Nonlinear Switched Systems with Adaptive Reinforcement Learning

  • Phuong Nam Dao,
  • Hong Quang Nguyen,
  • Minh-Duc Ngo and
  • Seon-Ju Ahn

27 September 2020

In this paper, a tracking control approach is developed based on an adaptive reinforcement learning algorithm with a bounded cost function for perturbed nonlinear switched systems, which represent a useful framework for modelling these converters, su...

(This article belongs to the Section F: Electrical Engineering)
  • Article
  • Open Access
1 Citations
4,513 Views
21 Pages

25 August 2018

This work demonstrates a formal connection between density estimation with a data-rate constraint and the joint objective of fixed-rate universal lossy source coding and model identification introduced by Raginsky in 2008 (IEEE TIT, 2008, 54, 3059&nd...

(This article belongs to the Special Issue Rate-Distortion Theory and Information Theory)
  • Article
  • Open Access
7 Citations
3,610 Views
18 Pages

Aircraft-LBDet: Multi-Task Aircraft Detection with Landmark and Bounding Box Detection

  • Yihang Ma,
  • Deyun Zhou,
  • Yuting He,
  • Liangjin Zhao and ,
  • Peirui Cheng,
  • Hao Li and
  • Kaiqiang Chen
  • + 2 authors+ 0 author

9 May 2023

With the rapid development of artificial intelligence and computer vision, deep learning has become widely used for aircraft detection. However, aircraft detection is still a challenging task due to the small target size and dense arrangement of airc...

(This article belongs to the Special Issue Multi-Modal and Multi-Task Learning in Photogrammetry and Remote Sensing)
  • Article
  • Open Access
28 Citations
2,609 Views
20 Pages

15 August 2024

This paper studies the single-machine scheduling problem with truncated learning effect, time-dependent processing time, and past-sequence-dependent delivery time. The delivery time is the time that the job is delivered to the customer after processi...

(This article belongs to the Section E1: Mathematics and Computer Science)
  • Article
  • Open Access
23 Citations
3,130 Views
19 Pages

CNN-Based Approaches with Different Tumor Bounding Options for Lymph Node Status Prediction in Breast DCE-MRI

  • Domiziana Santucci,
  • Eliodoro Faiella,
  • Michela Gravina,
  • Ermanno Cordelli and ,
  • Carlo de Felice,
  • Bruno Beomonte Zobel,
  • Giulio Iannello,
  • Carlo Sansone and
  • Paolo Soda
  • + 4 authors+ 0 author

21 September 2022

Background: The axillary lymph node status (ALNS) is one of the most important prognostic factors in breast cancer (BC) patients, and it is currently evaluated by invasive procedures. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), hi...

(This article belongs to the Special Issue Artificial Intelligence and MRI Characterization of Tumors)
  • Article
  • Open Access
65 Views
28 Pages

12 November 2026

Learning-based distribution system state estimation (DSSE) predictors trained with the squared loss estimate the conditional mean of the state given the measurements. Under contaminated measurements, the conditional mean shifts, and the unbounded inf...

(This article belongs to the Topic Mathematical Fundamentals of Machine Learning in Power Systems)
  • Article
  • Open Access
25 Citations
5,956 Views
15 Pages

Real-Time 3D Multi-Object Detection and Localization Based on Deep Learning for Road and Railway Smart Mobility

  • Antoine Mauri,
  • Redouane Khemmar,
  • Benoit Decoux,
  • Madjid Haddad and
  • Rémi Boutteau

12 August 2021

For smart mobility, autonomous vehicles, and advanced driver-assistance systems (ADASs), perception of the environment is an important task in scene analysis and understanding. Better perception of the environment allows for enhanced decision making,...

  • Article
  • Open Access
2 Citations
1,259 Views
28 Pages

9 January 2025

In this paper, the theoretical stability of batch offline action-dependent heuristic dynamic programming (BOADHDP) is analyzed for deep neural network (NN) approximators for both the action value function and controller which are iteratively improved...

  • Article
  • Open Access
1,089 Views
31 Pages

Accurate temperature prediction is essential for optimizing the microwave preheating of PET preforms prior to blow molding. A key challenge in this context is the strong dependence of electromagnetic field distributions and thermal responses on prefo...

  • Article
  • Open Access
2 Citations
3,492 Views
26 Pages

Elastic Information Bottleneck

  • Yuyan Ni,
  • Yanyan Lan,
  • Ao Liu and
  • Zhiming Ma

15 September 2022

Information bottleneck is an information-theoretic principle of representation learning that aims to learn a maximally compressed representation that preserves as much information about labels as possible. Under this principle, two different methods...

(This article belongs to the Special Issue Artificial Intelligence and Scientific Computing: Mathematical Techniques and Applications)
  • Article
  • Open Access
52 Citations
12,976 Views
21 Pages

Deep Learning for Mango (Mangifera indica) Panicle Stage Classification

  • Anand Koirala,
  • Kerry B. Walsh,
  • Zhenglin Wang and
  • Nicholas Anderson

18 January 2020

Automated assessment of the number of panicles by developmental stage can provide information on the time spread of flowering and thus inform farm management. A pixel-based segmentation method for the estimation of flowering level from tree images wa...

(This article belongs to the Special Issue In-Field Estimation of Fruit Quality and Quantity)
  • Article
  • Open Access
3 Citations
2,064 Views
22 Pages

19 March 2025

Unit commitment (UC) is a critical challenge in power system optimization, typically formulated as a high-dimensional mixed-integer linear programming (MILP) problem with non-deterministic polynomial-time hard (NP-hard) complexity. While the branch-a...

(This article belongs to the Section Electrical, Electronics and Communications Engineering)

of 40