-
Doubly stochastic subdomain mining with sample reweighting for unsupervised domain adaptive person re-identification AI Commun. (IF 0.8) Pub Date : 2024-01-19 Chunren Tang, Dingyu Xue, Dongyue Chen
Clustering-based unsupervised domain adaptive person re-identification methods have achieved remarkable progress. However, existing works are easy to fall into local minimum traps due to the optimization of two variables, feature representation and pseudo labels. Besides, the model can also be hurtby the inevitable false assignment of pseudo labels. In order to solve these problems, we propose the
-
Transductive classification via patch alignment AI Commun. (IF 0.8) Pub Date : 2024-01-12 Zhijun Song, Zhaoli Wu, Shu-Wen Chen, Hui-Sheng Zhu
In this paper, a novel approach for transductive classification is proposed. Unlike existing methods that heavily rely on constructing the Laplacian matrix to capture data distribution, the proposed approach takes a unique path. It employs a linear transformation model to create local patches for each data point and then unifies them in an objective function to build the Laplacian matrix. Incorporating
-
Temporally-aware node embeddings for evolving networks topologies AI Commun. (IF 0.8) Pub Date : 2024-01-02 Karen B. Enes, Matheus Nunes, Fabricio Murai, Gisele L. Pappa
Static node embedding algorithms applied to snapshots of real-world applications graphs are unable to capture their evolving process. As a result, the absence of information about the dynamics in these node representations can harm the accuracy and increase processing time of machine learning tasksrelated to these applications. Aiming at fill the gap regarding the inability of static methods to capture
-
Evolutionary multi-objective physics-informed neural networks: The MOPINNs approach AI Commun. (IF 0.8) Pub Date : 2023-12-15 Hugo Carrillo, Taco de Wolff, Luis Martí, Nayat Sanchez-Pi
Physics-informed neural networks formulation allows the neural network to be trained by both the training data and prior domain knowledge about the physical system that models the data. In particular, it has a loss function for the data and the physics, where the latter is the deviation from a partial differential equation describing the system. Conventionally, both loss functions are combined by a
-
Some thoughts about artificial stupidity and artificial dumbness AI Commun. (IF 0.8) Pub Date : 2023-12-14 Jean Lieber, Jean-Guy Mailly, Pierre Marquis, Henri Prade, François Rollin
In a recently published book, the French writer and comedian François Rollin has discussed various aspects of the notion of stupidity, including artificial stupidity, the stupid counterpart of artificial intelligence. His claim is that a system of artificial stupidity is a system that provides wrong answers to any task it should solve, leading to absurd solutions in most cases. We believe that this
-
Semantic segmentation based on enhanced gated pyramid network with lightweight attention module AI Commun. (IF 0.8) Pub Date : 2023-12-06 A. Viswanathan, V. Senthil kumar, M. Umamaheswari, Vignesh Janarthanan, M. Jaganathan
Semantic segmentation has made tremendous progress in recent years. The development of large datasets and the regression of convolutional models have enabled effective training of very large semantic model. Nevertheless, higher capacity indicates a higher computational problem, thus preventing real-time operation. Yet, due to the limited annotations, the models may have relied heavily on the available
-
A logical modeling of the Yōkai board game AI Commun. (IF 0.8) Pub Date : 2023-11-28 Jorge Fernandez, Dominique Longin, Emiliano Lorini, Frédéric Maris
We present an epistemic language for representing an artificial player’s beliefs and actions in the context of the Yōkai board game. Yōkai is a cooperative game which requires a combination of Theory of Mind (ToM), temporal and spatial reasoning to be played effectively by an artificial agent. We show that the language properly accounts for these three dimensions and that its satisfiability problem
-
Multi-objective hyperparameter optimization approach with genetic algorithms towards efficient and environmentally friendly machine learning AI Commun. (IF 0.8) Pub Date : 2023-11-23 André M. Yokoyama, Mariza Ferro, Bruno Schulze
This paper presents a multi-objective optimization approach for developing efficient and environmentally friendly Machine Learning models. The proposed approach uses Genetic Algorithms to simultaneously optimize the accuracy, time-to-solution, and energy consumption simultaneously. This solution proposed to be part of an Automated Machine Learning pipeline and focuses on architecture and hyperparameter
-
On the links between belief merging, the Borda voting method, and the cancellation property 1 AI Commun. (IF 0.8) Pub Date : 2023-11-17 Patricia Everaere, Chouaib Fellah, Sébastien Konieczny, Ramón Pino Pérez
In this work, we explore the links between the Borda voting rule and belief merging operators. More precisely, we define two families of merging operators inspired by the definition of the Borda voting rule. We also introduce a notion of cancellation in belief merging, inspired by the axiomatization of the Borda voting rule proposed by Young. This allows us to provide a characterization of the drastic
-
Constrained incomplete argumentation frameworks: Expressiveness, complexity and enforcement AI Commun. (IF 0.8) Pub Date : 2023-11-16 Jean-Guy Mailly
Operations like belief change or merging have been adapted to the context of abstract argumentation. However, these operations may require to express some uncertainty or some disjunction in the result, which is not representable in classical AFs. For this reason, some of these earlier works requirea set of AFs or a set of extensions as the outcome of the operation, somehow to represent a “disjunction”
-
An adaptive threshold based gait authentication by incorporating quality measures AI Commun. (IF 0.8) Pub Date : 2023-10-25 Sonia Das, Sukadev Meher, Upendra Kumar Sahoo
In this paper, an adaptive threshold-based gait authentication model is proposed, which incorporates the quality measure in the distance domain and maps them into the gradient domain to realize the optimal threshold of each gait sample, in contrast to the fixed threshold, as most of the authentication model utilizes. For accessing the quality measure of each gait, a gait covariate invariant generative
-
Effective training to improve DeepPilot AI Commun. (IF 0.8) Pub Date : 2023-10-24 L. Oyuki Rojas-Perez, Jose Martinez-Carranza
We present an approach to autonomous drone racing inspired by how a human pilot learns a race track. Human pilots drive around the track multiple times to familiarise themselves with the track and find key points that allow them to complete the track without the risk of collision. This paper proposes a three-stage approach: exploration, navigation, and refinement. Our approach does not require prior
-
Lifetime policy reuse and the importance of task capacity AI Commun. (IF 0.8) Pub Date : 2023-10-24 David M. Bossens, Adam J. Sobey
A long-standing challenge in artificial intelligence is lifelong reinforcement learning, where learners are given many tasks in sequence and must transfer knowledge between tasks while avoiding catastrophic forgetting. Policy reuse and other multi-policy reinforcement learning techniques can learnmultiple tasks but may generate many policies. This paper presents two novel contributions, namely 1) Lifetime
-
Dual cross-domain session-based recommendation with multi-channel integration AI Commun. (IF 0.8) Pub Date : 2023-10-13 Jinjin Zhang, Xiang Hua, Peng Zhao, Kai Kang
Session-based recommendation aims at predicting the next behavior when the current interaction sequence is given. Recent advances evaluate the effectiveness of dual cross-domain information for the session-based recommendation. However, we discover that accurately modeling the session representations is still a challenging problem due to the complexity of preference interactions in the cross-domain
-
Conflagration-YOLO: a lightweight object detection architecture for conflagration AI Commun. (IF 0.8) Pub Date : 2023-10-13 Ning Sun, Pengfei Shen, Xiaoling Ye, Yifei Chen, Xiping Cheng, Pingping Wang, Jie Min
Fire monitoring of fire-prone areas is essential, and in order to meet the requirements of edge deployment and the balance of fire recognition accuracy and speed, we design a lightweight fire recognition network, Conflagration-YOLO. Conflagration-YOLO is constructed by depthwise separable convolution and more attention to fire feature information extraction from a three-dimensional(3D) perspective
-
DW: Detected weight for 3D object detection AI Commun. (IF 0.8) Pub Date : 2023-10-05 Zhi Huang
It is a generic paradigm to treat all samples equally in 3D object detection. Although some works focus on discriminating samples in the training process of object detectors, the issue of whether a sample detects its target GT (Ground Truth) during training process has never been studied. In this work, we first point out that discriminating the samples that detect their target GT and the samples that
-
Multi-scale spatio-temporal network for skeleton-based gait recognition AI Commun. (IF 0.8) Pub Date : 2023-10-02 Dongzhi He, Yongle Xue, Yunyu Li, Zhijie Sun, Xingmei Xiao, Jin Wang
Gait has unique physiological characteristics and supports long-distance recognition, so gait recognition is ideal for areas such as home security and identity detection. Methods using graph convolutional networks usually extract features in the spatial and temporal dimensions by stacking GCNs andTCNs, but different joints are interconnected at different moments, so splitting the spatial and temporal
-
Transferring experiences in k-nearest neighbors based multiagent reinforcement learning: an application to traffic signal control AI Commun. (IF 0.8) Pub Date : 2023-09-27 Ana Lucia C. Bazzan, Vicente N. de Almeida, Monireh Abdoos
The increasing demand for mobility in our society poses various challenges to traffic engineering, computer science in general, and artificial intelligence in particular. Increasing the capacity of road networks is not always possible, thus a more efficient use of the available transportation infrastructure is required. Another issue is that many problems in traffic management and control are inherently
-
TMTrans: texture mixed transformers for medical image segmentation AI Commun. (IF 0.8) Pub Date : 2023-08-29 Lifang Chen, Tao Wang, Hongze Ge
Accurate segmentation of skin cancer is crucial for doctors to identify and treat lesions. Researchers are increasingly using auxiliary modules with Transformers to optimize the model’s ability to process global context information and reduce detail loss. Additionally, diseased skin texture differsfrom normal skin, and pre-processed texture images can reflect the shape and edge information of the diseased
-
Classifying falls using out-of-distribution detection in human activity recognition AI Commun. (IF 0.8) Pub Date : 2023-08-29 Debaditya Roy, Vangjush Komini, Sarunas Girdzijauskas
Abstract As the research community focuses on improving the reliability of deep learning, identifying out-of-distribution (OOD) data has become crucial. Detecting OOD inputs during test/prediction allows the model to account for discriminative features unknown to the model. This capability increases the model’s reliability since this model provides a class prediction solely at incoming data similar
-
Dynamic finegrained structured pruning sensitive to filter texture distribution AI Commun. (IF 0.8) Pub Date : 2023-08-25 Ping Li, Yuzhe Wang, Cong Wu, Xiatao Kang
Pruning of neural networks is undoubtedly a popular approach to cope with the current compression of large-scale, high-cost network models. However, most of the existing methods require a high level of human-regulated pruning criteria, which requires a lot of human effort to figure out a reasonablepruning strength. One of the main reasons is that there are different levels of sensitivity distribution
-
A heterogeneous two-stream network for human action recognition AI Commun. (IF 0.8) Pub Date : 2023-08-16 Shengbin Liao, Xiaofeng Wang, ZongKai Yang
The most widely used two-stream architectures and building blocks for human action recognition in videos generally consist of 2D or 3D convolution neural networks. 3D convolution can abstract motion messages between video frames, which is essential for video classification. 3D convolution neural networks usually obtain good performance compared with 2D cases, however it also increases computational
-
Fully Automated Neural Network Framework for Pulmonary Nodules Detection and Segmentation AI Commun. (IF 0.8) Pub Date : 2023-08-11 Yixin Xiong, Yongcheng Zhou, Yujuan Wang, Quanxing Liu, Lei Deng
Lung cancer is the leading cause of cancer death worldwide, and most patients are diagnosed with advanced stages for lack of symptoms in the early stages of the disease, leading to poor prognosis. It is thus of great importance to detect lung cancer in the early stages which can reduce mortality and improve patient survival significantly. Although there are many computer aided diagnosis (CAD) systems
-
Multi-agent reinforcement learning for safe lane changes by connected and autonomous vehicles: A survey AI Commun. (IF 0.8) Pub Date : 2023-08-11 Bharathkumar Hegde, Mélanie Bouroche
Connected Autonomous vehicles (CAVs) are expected to improve the safety and efficiency of traffic by automating driving tasks. Amongst those, lane changing is particularly challenging, as it requires the vehicle to be aware of its highly-dynamic surrounding environment, make decisions, and enact them within very short time windows. As CAVs need to optimise their actions based on a large set of data
-
Factoring textual reviews into user preferences in multi-criteria based content boosted hybrid filtering (MCCBHF) recommendation system AI Commun. (IF 0.8) Pub Date : 2023-08-11 Sivanaiah Rajalakshmi, R. Sakaya Milton, T.T. Mirnalinee
Recommendation systems help customers to find interesting and valuable resources in the internet services. Their priority is to create and examine users’ individual profiles, which contain their preferences, and then update their profile content with additional features to finally increase the users’ satisfaction. Specific characteristics or descriptions and reviews of the items to recommend also play
-
How to achieve fair and efficient cooperative vehicle routing? AI Commun. (IF 0.8) Pub Date : 2023-07-28 Aitor López Sánchez, Marin Lujak, Frederic Semet, Holger Billhardt
A cooperative is a business entity with the primary objective of providing benefits, services, and goods to its members, who both own and exercise democratic control over it. In the context of a cooperative, a fleet typically consists of vehicles owned by self-concerned individually rational ownerswho prioritize their own efficiency and the fairness of the system. This fairness refers to how their
-
Predicting the success of transfer learning for genetic programming using DeepInsight feature space alignment AI Commun. (IF 0.8) Pub Date : 2023-07-28 Leonardo Trujillo, Joel Nation, Luis Muñoz, Edgar Galván
In Transfer Learning (TL) a model that is trained on one problem is used to simplify the learning process on a second problem. TL has achieved impressive results for Deep Learning, but has been scarcely studied in genetic programming (GP). Moreover, predicting when, or why, TL might succeed is an open question. This work presents an approach to determine when two problems might be compatible for TL
-
A machine learning pipeline for extracting decision-support features from traffic scenes 1 AI Commun. (IF 0.8) Pub Date : 2023-07-14 Vitor A. Fraga, Lincoln V. Schreiber, Marco Antonio C. da Silva, Rafael Kunst, Jorge L.V. Barbosa, Gabriel de O. Ramos
Traffic systems play a key role in modern society. However, these systems are increasingly suffering from problems, such as congestions. A well-known way to efficiently reduce this kind of problem is to perform traffic light control intelligently through reinforcement learning (RL) algorithms. In this context, extracting relevant features from the traffic environment to support decision-making becomes
-
DL-PCN: Differential learning and parallel convolutional network for action recognition AI Commun. (IF 0.8) Pub Date : 2023-06-07 Qinyang Zeng, Ronghao Dang, Qin Fang, Chengju Liu, Qijun Chen
Graph Convolution Network (GCN) algorithms have greatly improved the accuracy of skeleton-based human action recognition. GCN can utilize the spatial information between skeletal joints in subsequent frames better than other deep learning algorithms, which is beneficial for achieving high accuracy.However, the traditional GCN algorithms consume lots of computation for the stack of multiple primary
-
FI-FPN: Feature-integration feature pyramid network for object detection AI Commun. (IF 0.8) Pub Date : 2023-06-05 Qichen Su, Guangjian Zhang, Shuang Wu, Yiming Yin
The multi-layer feature pyramid structure, represented by FPN, is widely used in object detection. However, due to the aliasing effect brought by up-sampling, the current feature pyramid structure still has defects, such as loss of high-level feature information and weakening of low-level small object features. In this paper, we propose FI-FPN to solve these problems, which is mainly composed of a
-
Multi-branch selection fusion fine-grained classification algorithm based on coordinate attention localization AI Commun. (IF 0.8) Pub Date : 2023-05-11 Feng Zhang, Gaocai Wang, Man Wu, Shuqiang Huang
Object localization has been the focus of research in Fine-Grained Visual Categorization (FGVC). With the aim of improving the accuracy and precision of object localization in multi-branch networks, as well as the robustness and universality of object localization methods, our study mainly focus onhow to combine coordinate attention and feature activation map for target localization. The model in this
-
Sound event localization and detection using element-wise attention gate and asymmetric convolutional recurrent neural networks AI Commun. (IF 0.8) Pub Date : 2023-04-20 Lean Yan, Min Guo, Zhiqiang Li
There are problems that standard square convolution kernel has insufficient representation ability and recurrent neural network usually ignores the importance of different elements within an input vector in sound event localization and detection. This paper proposes an element-wise attention gate-asymmetric convolutional recurrent neural network (EleAttG-ACRNN), to improve the performance of sound
-
The 11th IJCAR automated theorem proving system competition – CASC-J11 AI Commun. (IF 0.8) Pub Date : 2023-03-30 Geoff Sutcliffe, Martin Desharnais
The CADE ATP System Competition (CASC) is the annual evaluation of fully automatic, classical logic, Automated Theorem Proving (ATP) systems. CASC-J11 was the twenty-seventh competition in the CASC series. Twenty-four ATP systems competed in the various competition divisions. This paper presents anoutline of the competition design and a commentated summary of the results.
-
Automatic Chinese knowledge-based question answering by the MGBA-LSTM-CNN model AI Commun. (IF 0.8) Pub Date : 2023-03-13 Wenyuan Liu, Mingliang Fan, Kai Feng, Dingding Guo
The purpose of knowledge-based question answering (KBQA) is to accurately answer the questions raised by users through knowledge triples. Traditional Chinese KBQA methods rely heavily on artificial features, resulting in unsatisfactory QA results. To solve the above problems, this paper divides Chinese KBQA into two parts: entity extraction and attribute mapping. In the entity extraction stage, the
-
AdapTrack: An adaptive FairMOT tracking method applicable to marine ship targets AI Commun. (IF 0.8) Pub Date : 2023-03-02 Yantong Chen, Zekun Chen, Zhongling Zhang, Shichang Bian
Ship tracking at sea is faced with the disadvantages of complex sea conditions and the large influence of ship occlusion on the tracker. Therefore, we propose a method called AdapTrack based on On the Fairness of Detection and Re-Identification in Multiple Object Tracking (FairMOT) which is suitable for marine targets. The search strategy of trivial augmentation is used to randomly select suitable
-
PairTraining: A method for training Convolutional Neural Networks with image pairs AI Commun. (IF 0.8) Pub Date : 2023-02-10 Yuhong Shi, Yan Zhao, Chunlong Yao
In the field of image classification, the Convolutional Neural Networks (CNNs) are effective. Most of the work focuses on improving and innovating CNN’s network structure. However, using labeled data more effectively for training has also been an essential part of CNN’s research. Combining image disturbance and consistency regularization theory, this paper proposes a model training method (PairTraining)
-
Automatic prediction of epileptic seizure using hybrid deep ResNet-LSTM model AI Commun. (IF 0.8) Pub Date : 2023-01-23 Yajuvendra Pratap Singh, D.K. Lobiyal
Numerous advanced data processing and machine learning techniques for identifying epileptic seizures have been developed in the last two decades. Nonetheless, many of these solutions need massive data sets and intricate computations. Our approach transforms electroencephalogram (EEG) data into thetime-frequency domain by utilizing a short-time fourier transform (STFT) and the spectrogram (t-f) images
-
Defending against adversarial attacks on graph neural networks via similarity property AI Commun. (IF 0.8) Pub Date : 2023-01-23 Minghong Yao, Haizheng Yu, Hong Bian
Graph Neural Networks (GNNs) are powerful tools in graph application areas. However, recent studies indicate that GNNs are vulnerable to adversarial attacks, which can lead GNNs to easily make wrong predictions for downstream tasks. A number of works aim to solve this problem but what criteria we should follow to clean the perturbed graph is still a challenge. In this paper, we propose GSP-GNN, a general
-
Learning invariant representation using synthetic imagery for object detection AI Commun. (IF 0.8) Pub Date : 2022-12-30 Ning Jiang, Jinglong Fang, Yanli Shao
Recent years have witnessed a rapid advance in training and testing synthetic data through deep learning networks for the annotation of synthetic data can be automatically marked. However, domain discrepancy still exists between synthetic data and real data. In this paper, we address the domain discrepancy issue from three aspects: 1) We design a synthetic image generator with automatically labeled
-
Multimodal interaction aware embedding for location-based social networks AI Commun. (IF 0.8) Pub Date : 2022-12-12 Ruiyun Yu, Kang Yang, Zhihong Wang, Shi Zhen
Location-based social networks (LBSNs) have greatly promoted the development of the field of human mobility mining. However, the sparsity, multimodality and heterogeneity nature of the user check-in data remains a great concern for learning high-quality user or other entities representations, especially in the downstream application tasks, such as point-of-interest (POI) recommendation. Most existing
-
SECL: Sampling enhanced contrastive learning AI Commun. (IF 0.8) Pub Date : 2022-09-22 Yixin Tang, Hua Cheng, Yiquan Fang, Tao Cheng
Instance-level contrastive learning such as SimCLR has been successful as a powerful method for representation learning. However, SimCLR suffers from problems of sampling bias, feature bias and model collapse. A set-level based Sampling Enhanced Contrastive Learning based on SimCLR (SECL) is proposed in this paper. We use the proposed super-sampling method to expand the augmented samples into a contrastive-positive
-
Conversational AI for multi-agent communication in Natural Language AI Commun. (IF 0.8) Pub Date : 2022-09-20 Oliver Lemon
Research at the Interaction Lab focuses on human-agent communication using conversational Natural Language. The ultimate goal is to create systems where humans and AI agents (including embodied robots) can spontaneously form teams and coordinate shared tasks through the use of Natural Language conversation as a universal communication interface. This paper first introduces machine learning approaches
-
Reasoning and interaction for social artificial intelligence AI Commun. (IF 0.8) Pub Date : 2022-09-20 Elizabeth Black, Martim Brandão, Oana Cocarascu, Bart De Keijzer, Yali Du, Derek Long, Michael Luck, Peter McBurney, Albert Meroño-Peñuela, Simon Miles, Sanjay Modgil, Luc Moreau, Maria Polukarov, Odinaldo Rodrigues, Carmine Ventre
Current work on multi-agent systems at King’s College London is extensive, though largely based in two research groups within the Department of Informatics: the Distributed Artificial Intelligence (DAI) thematic group and the Reasoning & Planning (RAP) thematic group. DAI combines AI expertise withpolitical and economic theories and data, to explore social and technological contexts of interacting
-
Interaction-Oriented Software Engineering: Programming abstractions for autonomy and decentralization AI Commun. (IF 0.8) Pub Date : 2022-09-20 Amit K. Chopra
We review the main ideas and elements of Interaction-Oriented Software Engineering (IOSE), a program of research that we have pursued for the last two decades, a span of time in which it has grown from philosophy to practical programming abstractions. What distinguishes IOSE from any other programof research is its emphasis on supporting autonomy by modeling the meaning of communication and using that
-
Agent-based modelling for Urban Analytics: State of the art and challenges AI Commun. (IF 0.8) Pub Date : 2022-09-06 Nick Malleson, Mark Birkin, Daniel Birks, Jiaqi Ge, Alison Heppenstall, Ed Manley, Josie McCulloch, Patricia Ternes
Agent-based modelling (ABM) is a facet of wider Multi-Agent Systems (MAS) research that explores the collective behaviour of individual ‘agents’, and the implications that their behaviour and interactions have for wider systemic behaviour. The method has been shown to hold considerable value in exploring and understanding human societies, but is still largely confined to use in academia. This is particularly
-
Dependable learning-enabled multiagent systems AI Commun. (IF 0.8) Pub Date : 2022-09-06 Xiaowei Huang, Bei Peng, Xingyu Zhao
We are concerned with the construction, formal verification, and safety assurance of dependable multiagent systems. For the case where the system (agents and their environment) can be explicitly modelled, we develop formal verification methods over several logic languages, such as temporal epistemic logic and strategy logic, to reason about the knowledge and strategy of the agents. For the case where
-
Developing, evaluating and scaling learning agents in multi-agent environments AI Commun. (IF 0.8) Pub Date : 2022-09-06 Ian Gemp, Thomas Anthony, Yoram Bachrach, Avishkar Bhoopchand, Kalesha Bullard, Jerome Connor, Vibhavari Dasagi, Bart De Vylder, Edgar A. Duéñez-Guzmán, Romuald Elie, Richard Everett, Daniel Hennes, Edward Hughes, Mina Khan, Marc Lanctot, Kate Larson, Guy Lever, Siqi Liu, Luke Marris, Kevin R. McKee, Paul Muller, Julien Pérolat, Florian Strub, Andrea Tacchetti, Eugene Tarassov, Zhe Wang, Karl Tuyls
The Game Theory & Multi-Agent team at DeepMind studies several aspects of multi-agent learning ranging from computing approximations to fundamental concepts in game theory to simulating social dilemmas in rich spatial environments and training 3-d humanoids in difficult team coordination tasks. A signature aim of our group is to use the resources and expertise made available to us at DeepMind in deep
-
Resilience, reliability, and coordination in autonomous multi-agent systems AI Commun. (IF 0.8) Pub Date : 2022-09-06 Rafael C. Cardoso, Brian Logan, Felipe Meneguzzi, Nir Oren, Bruno Yun
Multi-agent systems is an evolving discipline that encompasses many different branches of research. The long-standing Agents at Aberdeen (A3) group undertakes research across several areas of multi-agent systems, focusing in particular on aspects related to resilience, reliability, and coordination. In this article we introduce the group and highlight past research successes in those themes, building
-
From intelligent agents to trustworthy human-centred multiagent systems AI Commun. (IF 0.8) Pub Date : 2022-09-06 Mohammad Divband Soorati, Enrico H. Gerding, Enrico Marchioni, Pavel Naumov, Timothy J. Norman, Sarvapali D. Ramchurn, Bahar Rastegari, Adam Sobey, Sebastian Stein, Danesh Tarpore, Vahid Yazdanpanah, Jie Zhang
The Agents, Interaction and Complexity research group at the University of Southampton has a long track record of research in multiagent systems (MAS). We have made substantial scientific contributions across learning in MAS, game-theoretic techniques for coordinating agent systems, and formal methods for representation and reasoning. We highlight key results achieved by the group and elaborate on
-
Perspectives on the system-level design of a safe autonomous driving stack AI Commun. (IF 0.8) Pub Date : 2022-09-02 Majd Hawasly, Jonathan Sadeghi, Morris Antonello, Stefano V. Albrecht, John Redford, Subramanian Ramamoorthy
Achieving safe and robust autonomy is the key bottleneck on the path towards broader adoption of autonomous vehicles technology. This motivates going beyond extrinsic metrics such as miles between disengagement, and calls for approaches that embody safety by design. In this paper, we address some aspects of this challenge, with emphasis on issues of motion planning and prediction. We do this through
-
Deep reinforcement learning for multi-agent interaction AI Commun. (IF 0.8) Pub Date : 2022-09-01 Ibrahim H. Ahmed, Cillian Brewitt, Ignacio Carlucho, Filippos Christianos, Mhairi Dunion, Elliot Fosong, Samuel Garcin, Shangmin Guo, Balint Gyevnar, Trevor McInroe, Georgios Papoudakis, Arrasy Rahman, Lukas Schäfer, Massimiliano Tamborski, Giuseppe Vecchio, Cheng Wang, Stefano V. Albrecht
The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Towards this goal, the Autonomous Agents Research Group develops novel machine learning algorithms for autonomous systemscontrol, with a specific focus on deep reinforcement learning and multi-agent reinforcement learning. Research
-
Emergent behaviours in multi-agent systems with Evolutionary Game Theory AI Commun. (IF 0.8) Pub Date : 2022-09-02 The Anh Han
The mechanisms of emergence and evolution of collective behaviours in dynamical Multi-Agent Systems (MAS) of multiple interacting agents, with diverse behavioral strategies in co-presence, have been undergoing mathematical study via Evolutionary Game Theory (EGT). Their systematic study also resorts to agent-based modelling and simulation (ABM) techniques, thus enabling the study of aforesaid mechanisms
-
Multi-agent systems for computational economics and finance AI Commun. (IF 0.8) Pub Date : 2022-09-01 Michael Kampouridis, Panagiotis Kanellopoulos, Maria Kyropoulou, Themistoklis Melissourgos, Alexandros A. Voudouris
In this article we survey the main research topics of our group at the University of Essex. Our research interests lie at the intersection of theoretical computer science, artificial intelligence, and economic theory. In particular, we focus on the design and analysis of mechanisms for systems involving multiple strategic agents, both from a theoretical and an applied perspective. We present an overview
-
Decision-making under uncertainty for multi-robot systems AI Commun. (IF 0.8) Pub Date : 2022-09-01 Bruno Lacerda, Anna Gautier, Alex Rutherford, Alex Stephens, Charlie Street, Nick Hawes
In this overview paper, we present the work of the Goal-Oriented Long-Lived Systems Lab on multi-robot systems. We address multi-robot systems from a decision-making under uncertainty perspective, proposing approaches that explicitly reason about the inherent uncertainty of action execution, and how such stochasticity affects multi-robot coordination. To develop effective decision-making approaches
-
Person re-identification based on multi-scale global feature and weight-driven part feature AI Commun. (IF 0.8) Pub Date : 2022-08-24 Qingwei Tang, Pu Yan, Jie Chen, Hui Shao, Fuyu Wang, Gang Wang
Person re-identification (ReID) is a crucial task in identifying pedestrians of interest across multiple surveillance camera views. ReID methods in recent years have shown that using global features or part features of the pedestrian is extremely effective, but many models do not have further design models to make more reasonable use of global and part features. A new model is proposed to use global
-
Cross-form efficient attention pyramidal network for semantic image segmentation AI Commun. (IF 0.8) Pub Date : 2022-08-09 Anamika Maurya, Satish Chand
Although convolutional neural networks (CNNs) are leading the way in semantic segmentation, standard methods still have some flaws. First, there is feature redundancy and less discriminating feature representations. Second, the number of effective multi-scale features is limited. In this paper, weaim to solve these constraints with the proposed network that utilizes two effective pre-trained models
-
An argumentative approach for handling inconsistency in prioritized Datalog± ontologies AI Commun. (IF 0.8) Pub Date : 2022-07-18 Loan Ho, Somjit Arch-int, Erman Acar, Stefan Schlobach, Ngamnij Arch-int
Prioritized Datalog± is a well-studied formalism for modelling ontological knowledge and data, and has a success story in many applications in the (Semantic) Web and in other domains. Since the information content on the Web is both inherently context-dependent and frequently updated, the occurrence of a logical inconsistency is often inevitable. This phenomenon has led the research community to develop
-
Improved YOLOv3 detection method for PCB plug-in solder joint defects based on ordered probability density weighting and attention mechanism AI Commun. (IF 0.8) Pub Date : 2022-07-15 Zheng Wang, Wenbin Chen, Taifu Li, Shaolin Zhang, Rui Xiong
Printed Circuit Board (PCB) is the heart component of electronic products, and its defect detection is the basic requirement of PCB quality control in the production process. Traditional visual detection methods need artificial design features, so their detection accuracy is poor, and the rate of missed and false detection is high. To solve the above problems, this paper proposes an improved YOLOv3
-
Channel attention and multi-scale graph neural networks for skeleton-based action recognition AI Commun. (IF 0.8) Pub Date : 2022-07-13 Ronghao Dang, Chengju Liu, Ming Liu, Qijun Chen
3D skeleton data has been widely used in action recognition as the skeleton-based method has achieved good performance in complex dynamic environments. The rise of spatio-temporal graph convolutions has attracted much attention to use graph convolution to extract spatial and temporal features together in the field of skeleton-based action recognition. However, due to the huge difference in the focus
-
Multiple refinement and integration network for Salient Object Detection AI Commun. (IF 0.8) Pub Date : 2022-05-10 Chao Dai, Chen Pan, Wei He, Hanqi Sun
The purpose of the salient object detection (SOD) task is to suppress the background noise and segment the salient foreground regions. Some previous methods considered the strategies of background suppression and multi-level feature fusion. Other methods encountered the problem that single-scale convolution features are difficult to capture the correct object size. This paper reconsiders the above