Skip to Content

258 Results Found

  • Article
  • Open Access
4 Citations
3,023 Views
16 Pages

27 December 2022

In recent years, human action recognition has received increasing attention as a significant function of human–machine interaction. The human skeleton is one of the most effective representations of human actions because it is highly compact an...

(This article belongs to the Special Issue Design, Dynamics and Control of Robots)
  • Article
  • Open Access
20 Citations
5,543 Views
21 Pages

Optimizing Water Use in Maize Irrigation with Reinforcement Learning

  • Muhammad Alkaff,
  • Abdullah Basuhail and
  • Yuslena Sari

11 February 2025

As global populations grow and environmental constraints intensify, improving agricultural water management is essential for sustainable food production. Traditional irrigation methods often lack adaptability, leading to inefficient water use. Reinfo...

(This article belongs to the Special Issue Advanced Image Processing and Computational Intelligence: Methodologies and Applications)
  • Article
  • Open Access
1 Citations
2,480 Views
20 Pages

25 April 2025

Action representations are essential for developing mutual cognition toward efficient human–AI collaboration, particularly in human–robot collaborative (HRC) workspaces. As such, it has become an emerging research direction for robots to...

(This article belongs to the Special Issue Bayesian Learning and Its Advanced Applications)
  • Article
  • Open Access
3 Citations
4,368 Views
18 Pages

24 October 2024

Conventional approaches to video action recognition perform global attention over the entire video patches, which may be ineffective due to the temporal redundancy of video frames. Recent works on masked video modeling adopt a high-ratio tube masking...

(This article belongs to the Collection Advances in Deep-Learning-Based Sensing, Imaging, and Video Processing)
  • Article
  • Open Access
3,167 Views
17 Pages

8 September 2021

Graph convolutional networks (GCNs), which model human actions as a series of spatial-temporal graphs, have recently achieved superior performance in skeleton-based action recognition. However, the existing methods mostly use the physical connections...

(This article belongs to the Collection Deep Learning for Computer Vision: Algorithms, Theory and Application)
  • Article
  • Open Access
13 Citations
6,925 Views
17 Pages

20 June 2020

We propose a new class of nonlocal Total Variation (TV), in which the first derivative and the second derivative are mixed. Since most existing TV considers only the first-order derivative, it suffers from problems such as staircase artifacts and los...

(This article belongs to the Special Issue Sensor Signal and Information Processing III)
  • Article
  • Open Access
1,058 Views
20 Pages

Diffusion-based trajectory planners achieve strong nominal performance in autonomous driving, but sparse safety intervention remains difficult to evaluate and realize effectively. This study addresses this problem by proposing a safety-aware event-tr...

(This article belongs to the Special Issue Application of Pattern Recognition and Machine Learning)
  • Article
  • Open Access
5 Citations
7,548 Views
14 Pages

Given the broad range of applications from video surveillance to human–computer interaction, human action learning and recognition analysis based on 3D skeleton data are currently a popular area of research. In this paper, we propose a method f...

(This article belongs to the Special Issue Innovation in Machine Intelligence for Critical Infrastructures)
  • Article
  • Open Access
1,617 Views
12 Pages

Traditional human behavior recognition needs many training samples. Signal transmission of images and videos via visible light in the body is crucial for detecting specific actions to accelerate behavioral recognition. Joint sparse representation tec...

(This article belongs to the Special Issue Smart Electronics, Energy, and IoT Infrastructures for Smart Cities)
  • Article
  • Open Access
2 Citations
6,338 Views
20 Pages

29 October 2013

Consider a setting in which agents can take one of two ordered actions and in which the incentive to take the high action increases in the number of other agents taking it. Furthermore, assume that we do not know anything else about the game being pl...

(This article belongs to the Special Issue Social Networks and Information Diffusion)
  • Article
  • Open Access
380 Views
16 Pages

Cluster Relation-Augmented Hierarchical Reinforcement Learning for Sparse Knowledge Graph Reasoning

  • Shun Mao,
  • Yinghan Hong,
  • Guizhen Mai,
  • Jiawei Li and ,
  • Zhao Chen,
  • Yike Li and
  • Dan Xiang
  • + 2 authors+ 0 author

Knowledge graphs (KGs) organize relational facts in a form that supports machine reasoning across many domains. In decentralized Internet of Things (IoT) environments, such graphs can describe interactions among distributed devices and services. Howe...

(This article belongs to the Special Issue Data Privacy and Protection in IoT Systems)
  • Article
  • Open Access
3,582 Views
27 Pages

29 December 2023

Among the numerous techniques followed to learn a linear classifier through the discriminative dictionary and sparse representations learning of signals, the techniques to learn a nonparametric Bayesian classifier jointly and discriminately with the...

(This article belongs to the Special Issue Novel Applications of Machine Learning and Bayesian Optimization)
  • Article
  • Open Access
11 Citations
5,700 Views
18 Pages

Episodic Self-Imitation Learning with Hindsight

  • Tianhong Dai,
  • Hengyan Liu and
  • Anil Anthony Bharath

21 October 2020

Episodic self-imitation learning, a novel self-imitation algorithm with a trajectory selection module and an adaptive loss function, is proposed to speed up reinforcement learning. Compared to the original self-imitation learning algorithm, which sam...

(This article belongs to the Special Issue Deep Reinforcement Learning: Methods and Applications)
  • Article
  • Open Access
6 Citations
5,517 Views
44 Pages

Long-Term Visitation Value for Deep Exploration in Sparse-Reward Reinforcement Learning

  • Simone Parisi,
  • Davide Tateo,
  • Maximilian Hensel,
  • Carlo D’Eramo and ,
  • Jan Peters and
  • Joni Pajarinen
  • + 1 author+ 0 author

28 February 2022

Reinforcement learning with sparse rewards is still an open challenge. Classic methods rely on getting feedback via extrinsic rewards to train the agent, and in situations where this occurs very rarely the agent learns slowly or cannot learn at all....

(This article belongs to the Special Issue Reinforcement Learning Algorithms)
  • Article
  • Open Access
2,759 Views
18 Pages

Language as an abstraction for hierarchical agents is promising to solve compositional long-time horizon decision-making tasks. The learning of the agent poses significant challenges, as it typically requires plenty of trajectories annotated with lan...

(This article belongs to the Special Issue AI in Knowledge-Based Information and Decision Support Systems)
  • Article
  • Open Access
23 Citations
7,247 Views
17 Pages

19 November 2022

Dyna-Q is a reinforcement learning method widely used in AGV path planning. However, in large complex dynamic environments, due to the sparse reward function of Dyna-Q and the large searching space, this method has the problems of low search efficien...

  • Article
  • Open Access
1 Citations
1,480 Views
20 Pages

22 October 2025

Hierarchical Reinforcement Learning (HRL) is effective for long-horizon and sparse-reward tasks by decomposing complex decision processes, but its real-world application remains limited due to instability between levels, inefficient subgoal schedulin...

(This article belongs to the Section Bioinspired Sensorics, Information Processing and Control)
  • Article
  • Open Access
14 Citations
4,067 Views
15 Pages

9 June 2019

An important outcome of social learning in the context of natural resource management is the potential for collective action—actions taken by a group of people that are the result of finding shared or common interest. Evidence of the relationsh...

(This article belongs to the Section Forest Ecology and Management)
  • Article
  • Open Access
6 Citations
2,407 Views
19 Pages

9 December 2020

In rescue operations, the full time of action plays important role. It is the sum of the planning, travel, and manipulation (in the action place) phase times. The time minimization of the first two phases by autonomous vehicle for remote action is co...

(This article belongs to the Section Systems & Control Engineering)
  • Article
  • Open Access
5 Citations
3,668 Views
24 Pages

We present a novel approach to generating a cooperative guidance strategy using deep reinforcement learning to address the challenge of cooperative multi-missile strikes under uncontrollable velocity conditions. This method employs the multi-agent pr...

(This article belongs to the Section Aeronautics)
  • Article
  • Open Access
3 Citations
3,206 Views
18 Pages

PMHR: Path-Based Multi-Hop Reasoning Incorporating Rule-Enhanced Reinforcement Learning and KG Embeddings

  • Ang Ma,
  • Yanhua Yu,
  • Chuan Shi,
  • Shuai Zhen and ,
  • Liang Pang and
  • Tat-Seng Chua
  • + 1 author+ 0 author

9 December 2024

Multi-hop reasoning provides a means for inferring indirect relationships and missing information from knowledge graphs (KGs). Reinforcement learning (RL) was recently employed for multi-hop reasoning. Although RL-based methods provide explainability...

(This article belongs to the Special Issue Future Technologies for Data Management, Processing and Application)
  • Article
  • Open Access
676 Views
22 Pages

With the continuous expansion and increasing topological complexity of modern power grids, achieving high-precision fault localization under sparse measurement conditions has become a core challenge in the operation and maintenance of smart grids. Ex...

  • Article
  • Open Access
88 Citations
8,052 Views
15 Pages

Autonomous Penetration Testing Based on Improved Deep Q-Network

  • Shicheng Zhou,
  • Jingju Liu,
  • Dongdong Hou,
  • Xiaofeng Zhong and
  • Yue Zhang

23 September 2021

Penetration testing is an effective way to test and evaluate cybersecurity by simulating a cyberattack. However, the traditional methods deeply rely on domain expert knowledge, which requires prohibitive labor and time costs. Autonomous penetration t...

(This article belongs to the Special Issue Machine Learning for Cybersecurity Threats, Challenges, and Opportunities Ⅱ)
  • Article
  • Open Access
4 Citations
3,863 Views
21 Pages

18 November 2020

In many applications of interacting systems, we are only interested in the dynamic behavior of a subset of all possible active species. For example, this is true in combustion models (many transient chemical species are not of interest in a given rea...

(This article belongs to the Special Issue Machine Learning for Prediction, Data Assimilation, and Uncertainty Quantification of Dynamical Systems)
  • Article
  • Open Access
21 Citations
3,619 Views
14 Pages

A Precise Nanostructure of Folate-Overhung Mitoxantrone DNA Tetrahedron for Targeted Capture Leukemia

  • Ying-Zi Bu,
  • Jia-Rui Xu,
  • Qian Luo,
  • Ming Chen and ,
  • Li-Min Mu and
  • Wan-Liang Lu
  • + 1 author+ 0 author

Regular chemotherapy cannot eliminate leukemic cells, due to the sparse distribution of cancer cells in leukemia patients. Here, we report a precise nanostructure of folate-overhung mitoxantrone DNA tetrahedron that enables the treatment of leukemic...

(This article belongs to the Section Biology and Medicines)
  • Article
  • Open Access
15 Citations
5,211 Views
20 Pages

7 May 2022

The simple and labor-intensive tasks of workers on the job site are rapidly becoming digital. In the work environment of logistics warehouses and manufacturing plants, moving goods to a designated place is a typical labor-intensive task for workers....

(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
  • Article
  • Open Access
44 Citations
15,593 Views
31 Pages

Changing the Environment Based on Empowerment as Intrinsic Motivation

  • Christoph Salge,
  • Cornelius Glackin and
  • Daniel Polani

21 May 2014

One aspect of intelligence is the ability to restructure your own environment so that the world you live in becomes more beneficial to you. In this paper we investigate how the information-theoretic measure of agent empowerment can provide a task-ind...

(This article belongs to the Special Issue Entropy Methods in Guided Self-Organization)
  • Article
  • Open Access
15 Citations
7,775 Views
18 Pages

4 April 2023

Wargames are essential simulators for various war scenarios. However, the increasing pace of warfare has rendered traditional wargame decision-making methods inadequate. To address this challenge, wargame-assisted decision-making methods that leverag...

(This article belongs to the Special Issue Applications of Artificial Intelligence and Machine Learning in Games)
  • Article
  • Open Access
901 Views
25 Pages

28 May 2026

Efficient coordination under limited communication is a central challenge in multi-agent reinforcement learning (MARL). Existing approaches often focus on message exchange without explicitly modeling how communication affects policy learning, leading...

(This article belongs to the Special Issue Advances in Multi-Agent Systems: Cooperative and Intelligent Control Strategies for Complex Applications)
  • Article
  • Open Access
1 Citations
1,728 Views
29 Pages

In constrained waters, multi-USV cooperative encirclement of highly maneuverable targets is strongly affected by partial observability as well as obstacle and boundary constraints, posing substantial challenges to stable cooperative control. Existing...

(This article belongs to the Section Ocean Engineering)
  • Systematic Review
  • Open Access
4 Citations
2,907 Views
22 Pages

17 December 2025

Many countries around the world require some or all schools to develop and implement a school improvement plan (SIP), which is a tool intended to guide the identification of school-specific needs for improvement along with a series of priorities, goa...

(This article belongs to the Special Issue Education Leadership: Challenges and Opportunities)
  • Article
  • Open Access
12 Citations
2,547 Views
17 Pages

11 April 2024

Surface electromyography (sEMG) signals are the sum of action potentials emitted by many motor units; they contain the information of muscle contraction patterns and intensity, so they can be used as a simple and reliable source for grasping mode rec...

(This article belongs to the Special Issue Advanced Robotics and Mechatronics)
  • Article
  • Open Access
5 Citations
5,934 Views
15 Pages

16 August 2016

Vision-based pedestrian detection has become an active topic in computer vision and autonomous vehicles. It aims at detecting pedestrians appearing ahead of the vehicle using a camera so that autonomous vehicles can assess the danger and take action....

(This article belongs to the Special Issue Sensors for Autonomous Road Vehicles)
  • Review
  • Open Access
25 Citations
8,016 Views
17 Pages

22 March 2023

The realization of the 2030 Agenda for Sustainable Development requires local governments globally to integrate Sustainable Development Goals (SDGs) into their policy and practice. In the case of the Hunter Valley Region of Australia, a key sustainab...

(This article belongs to the Section Health, Well-Being and Sustainability)
  • Article
  • Open Access
4 Citations
3,203 Views
16 Pages

To address the challenges of black-box video adversarial attacks, such as excessive query times and suboptimal attack performance due to the lack of result feedback during the attack process, we propose a reinforcement learning-based sparse adversari...

  • Article
  • Open Access
1,532 Views
26 Pages

A Multi-Source Feedback-Driven Framework for Generating WAF Test Cases

  • Pengcheng Lu,
  • Xiaofeng Zhong,
  • Wenbo Xu and
  • Yongjie Wang

20 March 2026

Web application firewalls (WAFs) are critical defenses against persistent threats to web applications, yet their security evaluation remains challenging. Traditional manual testing methods are often inefficient and resource-intensive, while existing...

(This article belongs to the Special Issue Adversarial Attacks and Cyber Security)
  • Perspective
  • Open Access
3 Citations
3,345 Views
8 Pages

22 September 2022

Ultrasound technology has therapeutic properties that can be harnessed to enhance topical drug delivery in a process known as phonophoresis. The literature on this method of drug delivery is currently sparse and scattered. In this review, we explore...

(This article belongs to the Special Issue Feature Papers in Therapy of Diabetic Foot Infections)
  • Article
  • Open Access
6 Citations
3,512 Views
27 Pages

1 November 2025

People are exposed to mixtures of metals, per- and polyfluoroalkyl substances (PFAS), phthalates, and polycyclic aromatic hydrocarbons (PAH) rather than single chemicals, yet mixture inference is hampered by high dimensionality, correlation, missingn...

  • Article
  • Open Access
948 Views
31 Pages

Adaptive 3D Human Pose Estimation Based on Spatial–Temporal Complexity Awareness

  • Wensi Zhang,
  • Ziyan Yang,
  • Chengfeng Hu,
  • Jing Sun and
  • Jie Li

Existing 3D human pose estimation methods use fixed computation strategies processing diverse action sequences, leading to computational redundancy for simple actions, insufficient high-frequency information capture for complex actions, and low long-...

(This article belongs to the Special Issue Advances in Real-Time Object Detection and Tracking)
  • Article
  • Open Access
391 Views
29 Pages

9 September 2026

As an emerging sensing modality, 4D millimeter-wave radar provides a privacy-preserving and lighting-robust solution for indoor scene perception and human action recognition (HAR). However, existing radar-based HAR methods mainly focus on short-term...

(This article belongs to the Special Issue Four-Dimensional Millimeter-Wave Radar: Design and Applications)
  • Article
  • Open Access
13 Citations
4,573 Views
20 Pages

Distributed Spectrum Management in Cognitive Radio Networks by Consensus-Based Reinforcement Learning

  • Dejan Dašić,
  • Nemanja Ilić,
  • Miljan Vučetić,
  • Miroslav Perić and ,
  • Marko Beko and
  • Miloš S. Stanković
  • + 1 author+ 0 author

23 April 2021

In this paper, we propose a new algorithm for distributed spectrum sensing and channel selection in cognitive radio networks based on consensus. The algorithm operates within a multi-agent reinforcement learning scheme. The proposed consensus strateg...

(This article belongs to the Special Issue Machine Learning Applied to Sensor Data Analysis)
  • Article
  • Open Access
12 Citations
4,539 Views
29 Pages

Deep CNN Sparse Coding for Real Time Inhaler Sounds Classification

  • Vaggelis Ntalianis,
  • Nikos Dimitris Fakotakis,
  • Stavros Nousias,
  • Aris S. Lalos and ,
  • Michael Birbas,
  • Evangelia I. Zacharaki and
  • Konstantinos Moustakas
  • + 2 authors+ 0 author

21 April 2020

Effective management of chronic constrictive pulmonary conditions lies in proper and timely administration of medication. As a series of studies indicates, medication adherence can effectively be monitored by successfully identifying actions performe...

(This article belongs to the Special Issue Real-Time Sensor Networks and Systems for the Industrial IoT)
  • Article
  • Open Access
36 Citations
8,449 Views
15 Pages

18 February 2022

Many devices have been used to detect human action, including wearable devices, cameras, lidars, and radars. However, some people, such as the elderly and young children, may not know how to use wearable devices effectively. Cameras have the disadvan...

(This article belongs to the Special Issue AI, Machine Learning and Deep Learning in Signal Processing)
  • Article
  • Open Access
1 Citations
1,646 Views
34 Pages

23 March 2026

This study proposes TNAP-DDQN, a deep reinforcement learning method for urban low-altitude UAV path planning under residential noise threshold constraints. With time cost and safety risk as the optimization objectives, operational constraints such as...

(This article belongs to the Section Innovative Urban Mobility)
  • Article
  • Open Access
7 Citations
4,346 Views
17 Pages

10 September 2022

The modeling, computational complexity, and accuracy of spatio-temporal models are the three major foci in the field of video action recognition. The traditional 2D convolution has low computational complexity, but it cannot capture the temporal rela...

(This article belongs to the Topic Machine and Deep Learning)
  • Article
  • Open Access
6 Citations
3,368 Views
13 Pages

30 November 2021

Graph convolutional networks (GCNs) have made significant progress in the skeletal action recognition task. However, the graphs constructed by these methods are too densely connected, and the same graphs are used repeatedly among channels. Redundant...

(This article belongs to the Topic Dynamical Systems: Theory and Applications)
  • Article
  • Open Access
749 Views
27 Pages

L-ARLPT: An LLM-Augmented Reinforcement Learning Framework for Autonomous Penetration Testing

  • Rufeng Zhan,
  • Junyi Zhu,
  • Yinghui Xu,
  • Chan Chen and ,
  • Rongxin Hu and
  • Le Wang
  • + 1 author+ 0 author

7 August 2026

In recent years, Deep Reinforcement Learning (DRL) has emerged as a promising approach for automating penetration testing due to its capability to perform sequential decision-making in complex environments. However, in real-world enterprise networks,...

(This article belongs to the Special Issue Advances in Deep Learning for Complex Combinatorial Optimization: Applications in Cybersecurity, Healthcare, and Intelligent Systems)
  • Commentary
  • Open Access
3 Citations
5,387 Views
6 Pages

The explosion of knowledge concerning the interplay of genetic and environmental factors determining pathophysiology and guiding therapeutic choice has altered the landscape in pediatric clinical pharmacology and pharmacy. The need for innovative res...

(This article belongs to the Collection Development of Medicines for Paediatric and Rare Diseases)
  • Article
  • Open Access
12 Citations
3,910 Views
28 Pages

Well Construction Action Planning and Automation through Finite-Horizon Sequential Decision-Making

  • Gurtej Singh Saini,
  • Oney Erge,
  • Pradeepkumar Ashok and
  • Eric van Oort

9 August 2022

Well construction operations require continuous complex decision-making and multi-step action planning. Action selection at every step demands a careful evaluation of the vast action space, while guided by long-term objectives and desired outcomes. C...

(This article belongs to the Topic Drilling, Completion and Well Engineering for the Natural Energy Resources Extraction, Storage and Sustainable Management)

of 6