Article
Computer Science, Artificial Intelligence
Wenping Ma, Xiaobo Zhou, Hao Zhu, Longwei Li, Licheng Jiao
Summary: The paper introduces a two-stage hybrid ACO algorithm for high-dimensional feature selection, which is capable of handling large-scale datasets efficiently with shorter running time.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Artificial Intelligence
Boyang Xu, Ali Asghar Heidari, Zhennao Cai, Huiling Chen
Summary: This study proposes a variant of the colony predation algorithm (CPA) called Covariance Gaussian cuckoo Colony Predation Algorithm (CGCPA), which employs a designed gaussian cuckoo variable dimensional strategy to enhance population diversity and global search ability, and a covariance matrix adaptation evolution strategy to enhance convergence speed and capture the global optimal solution. Experimental results show that CGCPA outperforms state-of-the-art algorithms in terms of convergence speed and accuracy.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Computer Science, Artificial Intelligence
A. Zhiwei Ye, B. Ruihan Li, C. Wen Zhou, D. Mingwei Wang, E. Mengqing Mei, F. Zhe Shu, G. Jun Shen
Summary: This paper proposes two innovative feature selection methods that integrate ant colony optimization (ACO) algorithm and hybrid rice optimization (HRO) to address the issue of redundant or irrelevant features in high-dimensional data analysis.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2023)
Article
Biology
Song Yang, Lejing Lou, Wangjia Wang, Jie Li, Xiao Jin, Shijia Wang, Jihao Cai, Fangjun Kuang, Lei Liu, Myriam Hadjouni, Hela Elmannai, Chang Cai
Summary: This paper proposes a new algorithm called SCACO, which combines slime mould foraging behavior and collaborative hunting to improve the convergence accuracy and solution quality of ACOR. It also optimizes the ability of ACO to jump out of local optima using an adaptive collaborative hunting strategy. The performance of SCACO is compared with nine basic algorithms and nine variants, demonstrating its effectiveness in classification prediction for the diagnosis of tuberculous pleural effusion.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Mathematics
Ibrahim Al-Shourbaji, Na Helian, Yi Sun, Samah Alshathri, Mohamed Abd Elaziz
Summary: This paper discusses the importance of feature selection in the telecommunications industry for machine learning models. It introduces a new approach that combines ant colony optimization and reptile search algorithm, and evaluates its performance in customer churn prediction.
Article
Computer Science, Artificial Intelligence
Sanchari Deb, Xiao-Zhi Gao
Summary: Transportation electrification is seen as a viable solution to global warming, air pollution, and energy crisis, but the optimal placement of charging infrastructure for Electric Vehicles presents a complex problem involving multiple design variables, objective functions, and constraints.
COMPLEX & INTELLIGENT SYSTEMS
(2022)
Article
Computer Science, Information Systems
Mrinalini Rana, Omdev Dahiya, Parminder Singh, Wadii Boulila, Adel Ammar
Summary: Data mining has become popular, but traditional methods are not sufficient with increasing data. Soft computing algorithms are used for mathematical optimization to obtain better results in less time. This paper proposes a framework for rule mining using a soft computing algorithm, specifically the Grouped-Artificial Bee Colony Optimization (G-ABC). The algorithm selects relevant attributes, verifies features, and applies mean-variance optimization and neural-based deep learning to validate the outcome.
Article
Engineering, Multidisciplinary
Adel Hamdan Mohammad, Sami Smadi, Tariq Alwada'n
Summary: This research proposes two models for spam detection and feature selection. The first model evaluates the dataset by reducing the number of keywords, and the results are promising. The second model creates features for spam detection and reduces the number of features using three metaheuristic algorithms, with highly significant outcomes.
CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Dickson Odhiambo Owuor, Thomas Runkler, Anne Laurent, Joseph Onderi Orero, Edmond Odhiambo Menya
Summary: Gradual pattern extraction is a field in Knowledge Discovery in Databases that aims to map correlations between attributes of a data set as gradual dependencies. In this study, three population-based optimization techniques are investigated to improve the efficiency of mining gradual patterns. The results show that ant colony optimization technique outperforms genetic algorithm and particle swarm optimization in the task of gradual pattern mining.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2021)
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, Theory & Methods
Joshua Peake, Martyn Amos, Nicholas Costen, Giovanni Masala, Huw Lloyd
Summary: This paper presents an improved algorithm for the Virtual Machine Placement (VMP) problem, which significantly improves the solution speed by utilizing parallelization techniques and modern processor technologies. The algorithm achieves solution qualities comparable to or even superior to other nature-inspired methods.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2022)
Article
Automation & Control Systems
Xiangbing Zhou, Hongjiang Ma, Jianggang Gu, Huiling Chen, Wu Deng
Summary: This paper proposes a parameter adaptation-based ant colony optimization (ACO) algorithm called PF3SACO, which combines particle swarm optimization (PSO), fuzzy system, and 3-Opt algorithm to improve the optimization ability and convergence, and avoid falling into local optima. The PF3SACO utilizes dynamic parameter adjustment and adaptive search to achieve better optimization performance, and applies 3-Opt algorithm to optimize the generated path.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Biochemical Research Methods
Yiyuan Chen, Yufeng Wang, Liang Cao, Qun Jin
Summary: The proposed Confidence-based and Cost-effective feature selection method (CCFS) utilizes BPSO to enhance healthcare data classification performance. By introducing a new updating mechanism and considering factors such as feature confidence, historical selection frequency, feature cost, and feature reduction ratio, the method has achieved promising experimental results.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2021)
Article
Computer Science, Artificial Intelligence
Mohsen Paniri, Mohammad Bagher Dowlatshahi, Hossein Nezamabadi-pour
Summary: This paper proposes a new multi-label feature selection method based on Ant Colony Optimization, using a heuristic learning approach to enhance performance. Experimental results demonstrate that the proposed method significantly outperforms competing methods.
SWARM AND EVOLUTIONARY COMPUTATION
(2021)
Article
Computer Science, Artificial Intelligence
Yi Fan, Pengjun Wang, Majdi Mafarja, Mingjing Wang, Xuehua Zhao, Huiling Chen
Summary: The fruit fly optimization algorithm (FOA) is a swarm-based algorithm inspired by fruit flies' food search behaviors in nature. The conventional FOA, while simple and concise, has limitations in exploration and exploitation abilities when used for different optimization problems. By introducing an improved FOA approach called BSSFOA, which utilizes bat sonar strategy for global optimization and a hybrid distribution mechanism for local optimization, better solutions can be found in both continuous and discrete optimization problems.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Information Systems
Fatemeh Shafiee, Mehrnoush Shamsfard
JOURNAL OF INFORMATION SCIENCE
(2018)
Article
Computer Science, Artificial Intelligence
Alireza Moayedikia
APPLIED SOFT COMPUTING
(2018)
Article
Computer Science, Artificial Intelligence
Shahram Salami, Mehrnoush Shamsfard
ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING
(2018)
Article
Computer Science, Interdisciplinary Applications
Zeinab Rahimi, Samira Noferesti, Mehrnoush Shamsfard
LANGUAGE RESOURCES AND EVALUATION
(2019)
Article
Computer Science, Artificial Intelligence
Neil Mac Parthalain, Richard Jensen, Ren Diao
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2020)
Article
Computer Science, Artificial Intelligence
Alireza Moayedikia, Hadi Ghaderi, William Yeoh
DECISION SUPPORT SYSTEMS
(2020)
Article
Computer Science, Information Systems
Batool Lakzaei, Mehrnoush Shamsfard
Summary: The article presents a new approach to automatically creating an OWL ontology from a relational database by defining a set of rules to analyze and extract ontology elements.
INFORMATION SCIENCES
(2021)
Article
Construction & Building Technology
Hadi Ghaderi, Pei-Wei Tsai, Lele Zhang, Alireza Moayedikia
Summary: Sustainable urban freight transport is a crucial aspect of the smart city concept, and the use of crowdshipping offers environmentally friendly last mile delivery options. This study proposes an integrated framework that utilizes trajectory analytics and an optimization module to assign delivery tasks to registered crowdshippers. The framework demonstrates satisfactory performance in terms of profit maximization, computational time, and environmental impact, as validated by real-world crowdshipping operations data.
SUSTAINABLE CITIES AND SOCIETY
(2022)
Article
Computer Science, Artificial Intelligence
Romina Etezadi, Mehrnoush Shamsfard
Summary: This paper presents a comparative study on question answering (QA) approaches and systems for answering complex questions. It discusses the definition of complex questions, surveys different types of constraints, addresses the challenges and methods proposed, and evaluates their strengths and weaknesses using benchmark datasets.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Software Engineering
Zeinab Rahimi, Mehrnoush Shamsfard
Summary: This study proposes a hybrid contradiction detection approach for detecting seven categories of contradictions in Persian texts, including antonymy, negation, numerical, factive, structural, lexical, and world knowledge. The approach consists of a novel data mining method and a transformer-based deep neural method. The data mining method extracts appropriate contradiction detection rules using frequent rule mining and tests them for different categories of contradictory sentences. The hybrid approach achieves an overall F-measure higher than 80%.
JOURNAL OF UNIVERSAL COMPUTER SCIENCE
(2023)
Article
Computer Science, Information Systems
Mozhgan Pourkeshavarz, Shahabedin Nabavi, Mohsen Ebrahimi Moghaddam, Mehrnoush Shamsfard
Summary: This paper proposes a stacked cross-modal feature consolidation (SCFC) attention network for image captioning, which combines high-level semantic concepts and visual information to generate fine-grained captions.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Somayyeh Behmanesh, Alireza Talebpour, Mehrnoush Shamsfard, Mohammad Mahdi Jafari
Summary: Recent AI studies have focused on developing question answering systems for automatic responses to natural language questions. Knowledge-based open domain question answering systems can accurately generate answers to questions in various fields. However, these systems require further development to scale answer retrieval and question interpretation. Deep learning methods are being used in this research area. Existing knowledge-based question answering systems use manually curated knowledge bases or knowledge bases automatically extracted from unstructured texts, or a combination of both. Limited access to knowledge bases in open domain question answering systems limits their expandability. Systems that use curated knowledge bases have high precision but limited coverage, while systems that use extracted knowledge bases have higher coverage but lower precision. To improve precision over extracted knowledge bases, a solution for enhancing relation span detection in questions is proposed in this paper. A dataset with 16,675 simple questions and answers based on Reverb triples is introduced. A method based on a fine-tuned BERT model is proposed for relation span detection in questions, resulting in a precision of 99.65%.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Soroush Mobasheri, Mehrnoush Shamsfard
Article
Business, Finance
Arezoo Ghahfarrokhi, Mehrnoush Shamsfard
INTELLIGENT SYSTEMS IN ACCOUNTING FINANCE & MANAGEMENT
(2020)
Proceedings Paper
Computer Science, Theory & Methods
Razieh Adelkhah, Mehrnoush Shamsfard, Niloofar Naderian
2019 5TH INTERNATIONAL CONFERENCE ON WEB RESEARCH (ICWR)
(2019)
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.