Article
Computer Science, Artificial Intelligence
Abdelrahman Elsaid, Karl Ricanek, Zimeng Lyu, Alexander Ororbia, Travis Desell
Summary: Continuous Ant-based Topology Search (CANTS) is a novel nature-inspired neural architecture search algorithm based on ant colony optimization. It utilizes a continuous search space to automate the design of artificial neural networks, removing the limitation of predetermined structure sizes. By adding an extra dimension for neural synaptic weights, CANTS can optimize both architecture and weights, significantly reducing optimization time while maintaining competitive performance.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Jing Liu, Sreenatha Anavatti, Matthew Garratt, Hussein A. Abbass
Summary: A multi-operator continuous Ant Colony Optimisation (MACO(R)) algorithm is proposed in this paper, which selects suitable operators based on historical performance and population status to improve search accuracy. Experimental results demonstrate the superiority of the proposed algorithm on real-world problems and investigate the impacts of multi-operator framework and different operator combinations on algorithm performance.
SWARM AND EVOLUTIONARY COMPUTATION
(2022)
Article
Computer Science, Artificial Intelligence
Jing Liu, Sreenatha Anavatti, Matthew Garratt, Hussein A. Abbass
Summary: This paper presents a continuous ant colony-based multi-UGV path planner, which optimizes the path for each UGV and resolves the collision avoidance problem for multi-agent coordination. Experimental results demonstrate the superiority of the proposed algorithm, especially in solving complex, high-dimensional problems.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Geography, Physical
Qingyang Wang, Guoqing Zhou, Ruhao Song, Yongfan Xie, Mengyuan Luo, Tao Yue
Summary: This paper proposes a novel method for selecting a mosaic seamline network in orthophotos using a continuous space ant colony algorithm. Experiments demonstrate that the proposed method achieves better performance compared to existing commercial software and algorithms.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2022)
Article
Multidisciplinary Sciences
Chuang Zhang, He Wang, Li-Hua Fu, Yue-Han Pei, Chun-Yang Lan, Hong-Yu Hou, Hua Song
Summary: Fruit-picking robots are important for promoting agricultural modernization and improving efficiency. By adopting the optimal sequential ant colony optimization algorithm (OSACO), which uses a continuous picking method, the robots can significantly improve their efficiency. The algorithm introduces innovative mechanisms to ensure global search capability and solve convergence problems. The results show that OSACO algorithm has better performance in terms of global search capability, convergence quality, path length, and robustness compared to other variants of the ant colony algorithm.
Article
Computer Science, Artificial Intelligence
Xinsen Zhou, Wenyong Gui, Ali Asghar Heidari, Zhennao Cai, Guoxi Liang, Huiling Chen
Summary: Continuous ant colony optimization algorithm incorporates a random following strategy to enhance global optimization performance and effectively handle high-dimensional feature selection problems. The algorithm performs competitively with other state-of-the-art algorithms in benchmark tests and outperforms well-known classification methods on high-dimensional datasets.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Information Systems
Jianlei Yang, Baoguo Yu, Shichen Li, Xuan Li, Shuo Li, Cheng Ci, Hong Wu
Summary: With the rapid development of the Internet and Internet of Things technology, location-based services have gained increasing attention. However, indoor positioning faces challenges due to the complex environment and interference factors. This paper proposes a fingerprint fusion positioning method using Wi-Fi, Frequency Modulation (FM), and Digital Terrestrial Multimedia Broadcast (DTMB) signals, which improves localization accuracy by 30% compared to Wi-Fi alone.
Article
Engineering, Electrical & Electronic
Branislav D. Batinic, Milos S. Arbanas, Jovan S. Bajic, Sandra R. Dedijer, Vladimir M. Rajs, Nikola M. Lakovic, Nenad R. Kulundzic
Summary: This article presents a machine learning-based application for estimating a reflected electromagnetic spectrum. By introducing artificial neural networks, the drawbacks from the previously used method were significantly reduced.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Computer Science, Artificial Intelligence
Dheeb Albashish, Abdulla Aburomman
Summary: This paper proposes a heterogeneous ensemble classifier configuration for a multiclass intrusion detection problem. The ensemble is composed of k-nearest neighbors, artificial neural networks, and naive Bayes classifiers, and the decisions of these classifiers are combined with weighted majority voting. The empirical study shows that the ensemble configuration using ACOR-optimized weights is capable of resolving conflicts between multiple classifiers and improving classification accuracy.
Article
Thermodynamics
Bin Sun, Zhenbiao Hu, Xiaojiang Liu, Zhao-Dong Xu, Dajun Xu
Summary: We have developed a physical model-free ant colony optimization network algorithm to predict the ceiling temperature distribution and maximal ceiling temperature in tunnel fires. Experimental results have shown the effectiveness and superiority of the algorithm, making it suitable for rapid fire disaster evaluation.
INTERNATIONAL JOURNAL OF THERMAL SCIENCES
(2022)
Article
Computer Science, Information Systems
Xiangmao Chang, Jiahua Dai, Zhiyong Zhang, Kun Zhu, Guoliang Xing
Summary: This article introduces a non-invasive radio-frequency respiratory volume monitoring system that continuously monitors user respiratory volume using commercial off-the-shelf RFID devices. By collecting temporal phase information from tags attached to the chest and abdomen, chest displacement and abdomen displacement caused by respiration are extracted and evaluated using a backpropagation neural network model to assess respiratory volume.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Optics
Dan Liu, Xiulian Hu, Qi Jiang
Summary: This paper combines the improved ant colony algorithm to study the logistics distribution path design and optimization. The fusion of genetic algorithm and improved ant colony algorithm transforms the path optimal solution into the initial distribution of pheromone, and the mutation operator expands the search space and accelerates the convergence to the optimal solution. The logistics distribution route optimization design and optimization method based on the improved ant colony algorithm proposed in this paper has good results.
Article
Automation & Control Systems
Jiao Liu, Yong Wang, Guangyong Sun, Tong Pang
Summary: This article introduces a new optimization algorithm, MiSACO, to solve complex optimization problems with both continuous and categorical variables. The algorithm utilizes multisurrogate-assisted selection and surrogate-assisted local search strategies, performing well in experiments.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Energy & Fuels
Adarsh Kumar Arya
Summary: This paper discusses the use of ant colony optimization strategy to minimize the operating costs of a natural gas pipeline grid. The study constructs a multi-objective modeling framework based on data from a French gas pipeline network corporation, focusing on reducing fuel usage in compressors and increasing throughput at distribution centers. The approach aims to guide pipeline managers in selecting the most preferred solutions by providing the optimum solution for each fuel consumption level at each compressor through a Pareto front analysis.
JOURNAL OF PETROLEUM EXPLORATION AND PRODUCTION TECHNOLOGY
(2021)
Article
Environmental Sciences
Ravinder Bhavya, Kaveri Sivaraj, Lakshmanan Elango
Summary: The quality of groundwater is crucial for human health and the environment, especially as it is the main source of drinking water in many parts of the world. Traditional water-quality monitoring methods are expensive and time-consuming, but data-driven models using artificial intelligence offer a more efficient way to predict groundwater quality. This study aims to build an optimized neural network using ant colony optimization and artificial neural network techniques for predicting groundwater quality parameters.
Article
Physics, Nuclear
Chencan Wang, Jinniu Hu, Ying Zhang, Hong Shen
JOURNAL OF PHYSICS G-NUCLEAR AND PARTICLE PHYSICS
(2020)
Article
Astronomy & Astrophysics
Hui Tong, Chencan Wang, Sibo Wang
Summary: The momentum and isospin dependence of the single-particle potential for the in-medium nucleon are investigated using the Relativistic Brueckner-Hartree-Fock (RBHF) theory in the full Dirac space. The calculations provide important insights into the saturation properties of symmetric and asymmetric nuclear matter, as well as the properties of neutron stars. The results from the full-Dirac-space RBHF theory are consistent with recent observations and have implications for gravitational wave detection.
ASTROPHYSICAL JOURNAL
(2022)
Article
Physics, Nuclear
Chencan Wang, Jinniu Hu, Ying Zhang, Hong Shen
Summary: In this study, the microscopic mechanisms of the symmetry energy in nuclear matter are investigated using the relativistic Brueckner-Hartree-Fock model with a high-precision realistic nuclear potential. The results show that the nucleon self-energy contributes positively to the symmetry energy, while the nucleon-nucleon interaction provides a negative contribution. The tensor force plays an important role in the symmetry energy, and the scalar and vector covariant amplitudes dominate the potential component of the symmetry energy.
Article
Plant Sciences
Boyang Liao, Chencan Wang, Xiaoxu Li, Yi Man, Hang Ruan, Yuanyuan Zhao
Summary: This study comprehensively analyzed the Populus trichocarpa laccase gene family and identified key laccase genes related to lignification. These findings not only provide new insights into the characteristics and functions of Populus laccase, but also give a new understanding of the broad prospects of plant laccase in lignocellulosic biofuel production.
FRONTIERS IN PLANT SCIENCE
(2023)
Review
Multidisciplinary Sciences
Li Xu, Hailin Hu, Chencan Wang, Xiaoxu Li, Wenjing Ding, Man Mel, Yuanyuan Zhao
Summary: Roots are important vegetative organs of plants that play various roles in plant lifecycle. The endodermis of roots acts as an extracellular barrier for selective nutrient absorption and undergoes differentiation stages to form Casparian strips and suberin lamellae structures. The structure of the endodermis can respond to stress and regulate ion homeostasis in plants. This paper comprehensively introduces the development mode, structure, composition, and formation regulation mechanism of the endodermis, highlighting its importance for plant adaptation and stress resistance.
CHINESE SCIENCE BULLETIN-CHINESE
(2023)
Article
Physics, Multidisciplinary
Xiaoying Qu, Hui Tong, Chencan Wang, Sibo Wang
Summary: A novel description of strongly interacting pure neutron matter (PNM) is presented using the relativistic Brueckner-Hartree-Fock (RBHF) theory. The scalar and vector components of the single-particle potentials are compared with RBHF calculations without negative-energy states. The results show that the binding energies of PNM are softer than those predicted by the Brueckner-Hartree-Fock theory with three-body forces, and are consistent with Monte Carlo simulations and many-body perturbation theory within uncertainties. The equation of state for neutron star matter is also in agreement with astrophysical observations and heavy-ion collision experiments. Additionally, the tidal deformabilities of binary neutron star systems are calculated and found to be consistent with observational constraints from GW170817.
SCIENCE CHINA-PHYSICS MECHANICS & ASTRONOMY
(2023)
Proceedings Paper
Physics, Nuclear
Peter Ring, Sibo Wang, Hui Tong, Qiang Zhao, Chencan Wang, Jie Meng
Summary: Considerable progress has been made in recent years in the ab-initio calculations of nuclear structure using non-relativistic many-body methods. The Dirac-Brueckner-Hartree-Fock theory offers a relativistic ab-initio approach that can reproduce the saturation properties of symmetric nuclear matter without three-body forces. However, the equations have only been solved for positive energy states, and the inclusion of negative energy states in various approximations has led to differences in isospin dependence. Recent efforts have solved this problem by providing a complete solution to the self-consistent relativistic Brueckner-Hartree-Fock equations in asymmetric nuclear matter. However, extending this theory to finite nuclear systems is challenging due to its numerical complexity.
13TH INTERNATIONAL SPRING SEMINAR ON NUCLEAR PHYSICS PERSPECTIVES AND CHALLENGES IN NUCLEAR STRUCTURE AFTER 70 YEARS OF SHELL MODEL, ISS 2022
(2023)
Article
Astronomy & Astrophysics
Pianpian Qin, Zhan Bai, Sibo Wang, Chencan Wang, Si-xue Qin
Summary: Starting from the relativistic Brueckner-Hartree-Fock theory for nuclear matter and the Dyson-Schwinger equation approach for quark matter, this study explores the possible hadron-quark phase transition in the interior of a neutron star. The first-order phase transition and crossover are studied using the Maxwell construction and three-window construction, respectively. The mass-radius relation and tidal deformability of the hybrid star are calculated and compared to observational and gravitational wave detection constraints.
Article
Physics, Nuclear
Hui Tong, Jing Gao, Chencan Wang, Sibo Wang
Summary: Relativistic Brueckner-Hartree-Fock (RBHF) theory in the full Dirac space is used to determine the momentum dependence of scalar and vector components of single-particle potentials. The method is applied to explore the properties of 208Pb by using the microscopic equation of state for asymmetric nuclear matter and a liquid droplet model. The neutron and proton density distributions, binding energies, radii, and neutron skin thickness in 208Pb are calculated. The charge densities predicted by the RBHF theory in the full Dirac space are compared with experimental data for elastic electron-nucleus scattering, showing good agreement. The uncertainty arising from variations of the surface term parameter f0 in the liquid droplet model is also discussed.
Article
Physics, Nuclear
Sibo Wang, Hui Tong, Qiang Zhao, Chencan Wang, Peter Ring, Jie Meng
Summary: The study investigates nucleon effective masses in neutron-rich matter using the relativistic Brueckner-Hartree-Fock (RBHF) theory in the full Dirac space. The effective masses of neutrons and protons in symmetric nuclear matter are consistent with empirical values. In neutron-rich matter, the neutron has a larger effective mass compared to the proton, and the predicted neutron-proton effective mass splittings at the empirical saturation density are related to the isospin asymmetry parameter. The study's results align with other ab initio calculations and constraints from nuclear reaction and structure measurements.
Article
Physics, Nuclear
Sibo Wang, Hui Tong, Qiang Zhao, Chencan Wang, Peter Ring, Jie Meng
Summary: The controversy surrounding isospin dependence of the effective Dirac mass in ab initio calculations of asymmetric nuclear matter is clarified through solving relativistic Brueckner-Hartree-Fock equations in full Dirac space. The symmetry energy and slope parameter at saturation density are in agreement with empirical values, and further applications predict neutron star radius and maximum mass.
Article
Chemistry, Multidisciplinary
Chen Wang, Haoran Deng, Hanying Zhao
Summary: Polymerization induced surface self-assembly (PISSA) technology is used to fabricate hierarchical surface nanostructures. The initiators for continuous activator regeneration (ICAR) atom transfer radical polymerization (ATRP)-induced PISSA approach is employed in this research to create surface nanostructures. The surface morphology changes gradually with an increase in monomer feeding ratio.
Article
Physics, Nuclear
Sibo Wang, Chencan Wang, Hui Tong
Summary: This article employs the relativistic Brueckner-Hartree-Fock (RBHF) theory to study neutron star properties, providing predictions for mass, moment of inertia, and quadrupole moment using various methods.
Article
Physics, Nuclear
Sibo Wang, Hui Tong, Chencan Wang
Summary: In this study, the relativistic Brueckner-Hartree-Fock equations are self-consistently solved for symmetric nuclear matter in the full Dirac space using the continuous choice for the single-particle potential. Inspired by nucleon-nucleon scattering in free space, the energy denominator of the scattering equation in the nuclear medium is rewritten to derive a complex Thompson equation for the effective interaction G matrix. By decomposing the matrix elements of the single-particle potential operator in the full Dirac space, both the real and imaginary parts of the single-particle potential are uniquely determined. The convergence of the hole-line expansion is discussed by comparing the equation of state obtained within the continuous choice with those obtained within the gap choice and in-between choice.
Proceedings Paper
Computer Science, Theory & Methods
Chen-can Wang, Yan Ge, Yang Li
Summary: In this study, an anomaly location data recognition method based on the improved YOLO algorithm is proposed to address the issue of poor accuracy in existing methods. By optimizing the algorithm design, a more accurate and noise-insensitive contour curve is obtained, and experimental results demonstrate the effectiveness and stability of the method.
ADVANCED HYBRID INFORMATION PROCESSING, PT I
(2022)
Article
Computer Science, Artificial Intelligence
Rui Lv, Dingheng Wang, Jiangbin Zheng, Zhao-Xu Yang
Summary: In this paper, the authors investigate tensor decomposition for neural network compression. They analyze the convergence and precision of tensor mapping theory, validate the rationality of tensor mapping and its superiority over traditional tensor approximation based on the Lottery Ticket Hypothesis. They propose an efficient method called 3D-KCPNet to compress 3D convolutional neural networks using the Kronecker canonical polyadic (KCP) tensor decomposition. Experimental results show that 3D-KCPNet achieves higher accuracy compared to the original baseline model and the corresponding tensor approximation model.
Article
Computer Science, Artificial Intelligence
Xiangkun He, Zhongxu Hu, Haohan Yang, Chen Lv
Summary: In this paper, a novel constrained multi-objective reinforcement learning algorithm is proposed for personalized end-to-end robotic control with continuous actions. The approach trains a single model using constraint design and a comprehensive index to achieve optimal policies based on user-specified preferences.
Article
Computer Science, Artificial Intelligence
Zhijian Zhuo, Bilian Chen, Shenbao Yu, Langcai Cao
Summary: In this paper, a novel method called Expansion with Contraction Method for Overlapping Community Detection (ECOCD) is proposed, which utilizes non-negative matrix factorization to obtain disjoint communities and applies expansion and contraction processes to adjust the degree of overlap. ECOCD is applicable to various networks with different properties and achieves high-quality overlapping community detection.
Article
Computer Science, Artificial Intelligence
Yizhe Zhu, Chunhui Zhang, Jialin Gao, Xin Sun, Zihan Rui, Xi Zhou
Summary: In this work, the authors propose a Contrastive Spatio-Temporal Distilling (CSTD) approach to improve the detection of high-compressed deepfake videos. The approach leverages spatial-frequency cues and temporal-contrastive alignment to fully exploit spatiotemporal inconsistency information.
Review
Computer Science, Artificial Intelligence
Laijin Meng, Xinghao Jiang, Tanfeng Sun
Summary: This paper provides a review of coverless steganographic algorithms, including the development process, known contributions, and general issues in image and video algorithms. It also discusses the security of coverless steganography from theoretical analysis to actual investigation for the first time.
Article
Computer Science, Artificial Intelligence
Yajie Bao, Tianwei Xing, Xun Chen
Summary: Visual question answering requires processing multi-modal information and effective reasoning. Neural-symbolic learning is a promising method, but current approaches lack uncertainty handling and can only provide a single answer. To address this, we propose a confidence based neural-symbolic approach that evaluates NN inferences and conducts reasoning based on confidence.
Article
Computer Science, Artificial Intelligence
Anh H. Vo, Bao T. Nguyen
Summary: Interior style classification is an interesting problem with potential applications in both commercial and academic domains. This project proposes a method named ISC-DeIT, which combines data-efficient image transformer architectures and knowledge distillation, to address the interior style classification problem. Experimental results demonstrate a significant improvement in predictive accuracy compared to other state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Shashank Kotyan, Danilo Vasconcellos Vargas
Summary: This article introduces a novel augmentation technique called Dynamic Scanning Augmentation to improve the accuracy and robustness of Vision Transformer (ViT). The technique leverages dynamic input sequences to adaptively focus on different patches, resulting in significant changes in ViT's attention mechanism. Experimental results demonstrate that Dynamic Scanning Augmentation outperforms ViT in terms of both robustness to adversarial attacks and accuracy against natural images.
Article
Computer Science, Artificial Intelligence
Hiba Alqasir, Damien Muselet, Christophe Ducottet
Summary: The article proposes a solution to improve the learning process of a classification network by providing shape priors, reducing the need for annotated data. The solution is tested on cross-domain digit classification tasks and a video surveillance application.
Article
Computer Science, Artificial Intelligence
Dexiu Ma, Mei Liu, Mingsheng Shang
Summary: This paper proposes a method using neural dynamics solvers to solve infinity-norm optimization problems. Two improved solvers are constructed and their effectiveness and superiority are demonstrated through theoretical analysis and simulation experiments.
Article
Computer Science, Artificial Intelligence
Francesco Gregoretti, Giovanni Pezzulo, Domenico Maisto
Summary: Active Inference is a computational framework that uses probabilistic inference and variational free energy minimization to describe perception, planning, and action. cpp-AIF is a header-only C++ library that provides a powerful tool for implementing Active Inference for Partially Observable Markov Decision Processes through multi-core computing. It is cross-platform and improves performance, memory management, and usability compared to existing software.
Article
Computer Science, Artificial Intelligence
Zelin Ying, Dawei Cheng, Cen Chen, Xiang Li, Peng Zhu, Yifeng Luo, Yuqi Liang
Summary: This paper proposes a novel stock market trends prediction framework called SMART, which includes a self-supervised stock technical data sequence embedding model S3E. By training with multiple self-supervised auxiliary tasks, the model encodes stock technical data sequences into embeddings and uses the learned sequence embeddings for predicting stock market trends. Extensive experiments on China A-Shares market and NASDAQ market prove the high effectiveness of our model in stock market trends prediction, and its effectiveness is further validated in real-world applications in a leading financial service provider in China.
Article
Computer Science, Artificial Intelligence
Hao Li, Hao Jiang, Dongsheng Ye, Qiang Wang, Liang Du, Yuanyuan Zeng, Liu Yuan, Yingxue Wang, C. Chen
Summary: DHGAT1, a dynamic hyperbolic graph attention network, utilizes hyperbolic metric properties to embed dynamic graphs. It employs a spatiotemporal self-attention mechanism and weighted node representations, resulting in excellent performance in link prediction tasks.
Article
Computer Science, Artificial Intelligence
Jiehui Huang, Zhenchao Tang, Xuedong He, Jun Zhou, Defeng Zhou, Calvin Yu-Chian Chen
Summary: This study proposes a progressive learning multi-scale feature blending model for image deraining tasks. The model utilizes detail dilation and texture extraction to improve the restoration of rainy images. Experimental results show that the model achieves near state-of-the-art performance in rain removal tasks and exhibits better rain removal realism.
Article
Computer Science, Artificial Intelligence
Lizhi Liu, Zilin Gao, Yinhe Wang, Yongfu Li
Summary: This paper proposes a novel discrete-time interconnected model for depicting complex dynamical networks. The model consists of nodes and edges subsystems, which consider the dynamic characteristic of both nodes and edges. By designing control strategies and coupling modes, the stabilization and synchronization of the network are achieved. Simulation results demonstrate the effectiveness of the proposed methods.