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, Artificial Intelligence
Jieguang He, Zhiping Peng, Jinbo Qiu, Delong Cui, Qirui Li
Summary: This study proposes a novel elitist fruit fly optimization algorithm (EFOA) to address the issues of poor population diversity and imbalance between global exploration and local exploitation in the original fruit fly optimization algorithm (FOA). EFOA consists of two search phases with elite and random individual guiding, and incorporates the use of elite and boundary information to enhance population diversity. The experimental results show that the elite guiding strategy and the alternating execution of the three search stages in EFOA effectively balance exploration and exploitation, and improve its convergence speed.
Article
Mathematics
Bin Yin, Jie Yang, Yue Li
Summary: This article proposes an improved fruit fly optimization algorithm by introducing evolutionary strategies to address the premature convergence and local extreme value problems of FOA. Experimental tests show that the improved algorithm performs well in terms of optimization ability and inversion accuracy.
JOURNAL OF MATHEMATICS
(2023)
Article
Mathematics, Interdisciplinary Applications
M. A. El-Shorbagy
Summary: This article presents a chaotic fruit fly algorithm (CFFA) as an optimization approach for solving engineering design problems. CFFA combines the fruit fly algorithm (FFA) with chaotic local search (CLS) to address the difficulties of the basic FFA in optimization problems.
Article
Computer Science, Theory & Methods
R. Roselin Kiruba, T. Sree Sharmila
Summary: The efficient image steganography using FOIS algorithm proposed in this work aims to safeguard medical data and prevent cybercrimes. By adaptively determining the optimal locations of pixels on the cover image, this method improves image quality and secures data effectively.
MULTIDIMENSIONAL SYSTEMS AND SIGNAL PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Sajjad Molaei, Hadi Moazen, Samad Najjar-Ghabel, Leili Farzinvash
Summary: The article introduces a new variant of PSO algorithm, PSOLC, which enhances its search performance through improved learning strategy and crossover operator. By altering exemplar particles, updating parameters, and integrating with genetic algorithm, the algorithm shows significant improvements in exploration and exploitation capabilities.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Interdisciplinary Applications
Helong Yu, Wenshu Li, Chengcheng Chen, Jie Liang, Wenyong Gui, Mingjing Wang, Huiling Chen
Summary: The Fruit Fly Optimization Algorithm (FOA) is a recently developed algorithm inspired by the foraging behavior of fruit fly populations. In order to improve its global search capability and solution quality, a dynamic step length mechanism, abandonment mechanism, and Gaussian bare-bones mechanism are introduced into FOA, resulting in BareFOA. Experimental results demonstrate that BareFOA outperforms other competitors in benchmark problems and engineering optimization design problems.
ENGINEERING WITH COMPUTERS
(2022)
Article
Computer Science, Information Systems
Broderick Crawford, Ricardo Soto, Hanns de la Fuente Mella, Claudio Elortegui, Wenceslao Palma, Claudio Torres-Rojas, Claudia Vasconcellos-Gaete, Marcelo Becerra, Javier Pena, Sanjay Misra
Summary: The paper discusses the application of the Fruit Fly Algorithm in dealing with binary-based combinatorial problems and how different binarization methods can be used to adapt the algorithm to binary search spaces. Experimental results show that the proposed algorithm is robust enough to handle the Set Coverage Problem effectively.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Computer Science, Information Systems
Zhuang Yang, Zengping Chen, Cheng Wang
Summary: SARAH method's performance relies on the choice of step size sequence, leading to the proposal of MB-SARAH-RBB method, which is proven to linearly converge in expectation for strongly convex objective functions and has better gradient complexity. Numerical experiments show the superiority of the proposed methods.
INFORMATION SCIENCES
(2021)
Article
Engineering, Multidisciplinary
Huajuan Huang, Dao Tao, Xiuxi Wei, Yongquan Zhou
Summary: An adaptive image enhancement algorithm based on a variable step size fruit fly optimization algorithm and a nonlinear beta transform is proposed in this paper to overcome the inefficiency and instability of manual methods. The algorithm optimizes the adjustment parameters of the nonlinear beta transform using the intelligent optimization characteristics of the fruit fly algorithm, resulting in improved image enhancement effects.
Article
Computer Science, Information Systems
Qian Cao, Bo Liu, Ying Jin
Summary: The paper proposes a Fruit Fly Optimization Algorithm based on Locality Sensitive Hashing-aware (LSHFOA) to address the weak global optimization ability of the Fruit fly Optimization Algorithm (FOA). The LSHFOA improves individual diversity of the population using locality sensitive hashing mechanism, and jumps out of local optimum by changing the population location. Experimental results show that LSHFOA has faster convergence speed and higher precision for function optimization.
JOURNAL OF CLOUD COMPUTING-ADVANCES SYSTEMS AND APPLICATIONS
(2022)
Article
Mathematics
Hazem Issa, Jozsef K. Tar
Summary: Model-based controllers can be affected by modeling imprecisions, but adaptive techniques and model improvement can compensate for these effects. This paper investigates the use of particle swarm optimization (PSO) to refine the model and combines it with an adaptive controller. The results show that this approach can improve the operation of the controller.
Article
Engineering, Multidisciplinary
Cheng He, Tao Wu, Runwei Gu, Zhongyan Jin, Renjie Ma, Huaying Qu
Summary: A fault diagnosis model based on composite multiscale permutation entropy and optimized extreme learning machine was proposed, showing higher fault diagnosis recognition rate through signal decomposition, feature vector calculation, and model optimization.
Article
Biology
Mohammed A. Awadallah, Mohammed Azmi Al-Betar, Malik Shehadeh Braik, Abdelaziz Hammouri, Iyad Abu Doush, Raed Abu Zitar
Summary: An enhanced binary version of the Rat Swarm Optimizer (RSO) is proposed for Feature Selection (FS) problems, showing superior performance over other methods on some datasets.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Chemistry, Analytical
Suganya Selvaraj, Eunmi Choi
Summary: This paper proposes an improved PSO algorithm, called dynamic sub-swarm PSO, for text document clustering problems. The experimental results show that this algorithm outperforms standard PSO and K-means algorithms in terms of purity and execution time.
Article
Automation & Control Systems
Qi Liu, Jindong Li, Lei Wu, Fengde Wang, Wensheng Xiao
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2020)
Article
Engineering, Environmental
Dongdong Yang, Guoming Chen, Jianmin Fu, Yuan Zhu, Ziliang Dai, Lei Wu, Jian Liu
Summary: Ventilation is an available measure to dilute toxic gas in offshore facilities, but its effectiveness needs further study, especially in emergency evacuation scenarios; Grid-based approach can identify the initial position with the worst toxic impact and estimate the effectiveness of ventilation; The research results can guide the improvement of safety in design and emergency plans for H2S release accidents.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2021)
Article
Automation & Control Systems
Lei Wu, Xinming Li, Chao Liu, Wensheng Xiao
Summary: A novel heuristic approach NHACR was proposed to solve the 2D rectangle packing problem with central rectangles, improving performance through three new strategies. The NHACR outperformed existing algorithms in terms of success rate, filling rate of final layout, and computing time across two benchmark sets, confirming its advantage in solving specific application problems in the oil and gas industry.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2021)
Article
Engineering, Mechanical
Qi Liu, Fengde Wang, Jindong Li, Wensheng Xiao
Summary: This study proposes a hybrid support vector regression method with multi-domain features to increase the accuracy of low-velocity impact localization on composite plate structures of ships. By incorporating signal preprocessing, feature extraction, and impact localization, the method effectively improves the localization performance. Experimental results demonstrate the satisfactory effectiveness of the proposed method in handling low-velocity impact localization issues on CFRP plates.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Chao Liu, Lei Wu, Xiaodong Huang, Wensheng Xiao
Summary: Pipe routing design (PRD) is an important problem in many industry fields, and the ant colony optimization (ACO) algorithm is a commonly used method for solving PRD. This study proposes an improved dynamic adaptive ACO (IDAACO) algorithm and verifies its effectiveness and advantages in solving PRD problems through experiments.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Engineering, Multidisciplinary
Qiming Shu, Lei Wu, Shunzhi Lu, Wensheng Xiao
Summary: In this study, a nonintrusive high-sensitivity sensitization structure for pipeline pressure detection is proposed based on fiber Bragg grating (FBG) sensor. The structure, which amplifies the strain of the pipeline wall, is validated to have a remarkable stability and effective transmission. It has potential application prospect for pressure monitoring of oil and gas pipelines.
Article
Optics
Shun Wang, Yaowen Yang, Lei Wu, Lipi Mohanty, Rui-Bo Jin, Liang Zhang, Peixiang Lu
Summary: Translating interferometric applications into practical field use with the required flexible precision and measurement range is challenging. An in-situ adjustable fiber-optic piezometer based on external Fabry-Perot interferometers (EFPIs) is demonstrated, utilizing the Vernier effect and its harmonics for water level measurement. The proposed scheme offers in-situ adjustable sensitivity, measurement range, simplicity, robustness, and remote sensing capability, making it suitable for various practical applications.
Article
Computer Science, Artificial Intelligence
Qi Liu, Mengxue Liu, Fengde Wang, Wensheng Xiao
Summary: This paper proposes a novel metaheuristic algorithm, called Dynamic Stochastic Search (DSS), for high-dimensional optimization problems. DSS effectively combines exploration and exploitation processes through a dynamic search control factor, a Gaussian distribution-based search process, two shrink modes inspired by the Whale Optimization Algorithm, and a balance mechanism derived from the Bat Algorithm. Experimental results show that DSS outperforms various advanced optimization algorithms in terms of convergence performance and efficiency for high-dimensional optimization problems.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Engineering, Multidisciplinary
Lei Wu, Shunzhi Lu, Heen Zhang, Qiming Shu, Wensheng Xiao
Summary: This study proposes a non-intrusive structure with high sensitivity based on fiber Bragg grating sensing for pipeline pressure detection. Experimental results show that the structure has the ability to amplify strain on the pipeline wall, and it also has advantages of convenient installation and simple structure.
Article
Computer Science, Artificial Intelligence
Lei Wu, Jiangtao Mei, Shuo Zhao
Summary: In this study, a novel method that combines artificial neural network and swarm intelligence algorithm is proposed to improve the accuracy of pipeline damage identification. Experimental results demonstrate that the proposed method is effective and accurate in different damage states.
APPLIED INTELLIGENCE
(2023)
Article
Chemistry, Physical
Zhongyan Liu, Shunzhi Lu, Deguo Wang, Yanbao Guo, Lei Wu
Summary: A non-intrusive and high-sensitivity structure for continuously monitoring pipeline pressure based on FBG sensor is proposed in this study. The structure demonstrates good strain sensitivity and its functionality is verified through laboratory experiments. It shows promising prospects for practical application.
Article
Engineering, Multidisciplinary
Xiaoming Chen, Siyi Cheng, Kaiqiang Wen, Chunjiang Wang, Jie Zhang, Han Zhang, Hechuan Ma, Lei Wu, Tianliang Li, Baotong Li, Jinyou Shao
Summary: This study integrated piezoelectric zinc oxide nanowires into carbon fiber reinforced composites, enabling self-sensing of damage. The results showed comparable performance to common damage detection techniques and improved mechanical properties of the composites.
COMPOSITES PART B-ENGINEERING
(2023)
Article
Engineering, Multidisciplinary
Yangyang Wang, Min Lou, Lingzhi Yang, Lei Wu
Summary: This work investigates the tensile properties of reinforced thermoplastic pipes (RTPs) under different internal pressures and temperatures. A new mechanical model of RTPs is proposed, and the effect of parameters such as internal pressure, winding angle, and temperature on the tensile properties is studied. Experimental results show that internal pressure has little influence on RTPs' tensile properties during the elastic stage but significantly affects them after the elastic limit. The winding angle and temperature also have significant effects on RTPs' tensile properties.
INTERNATIONAL JOURNAL OF PRESSURE VESSELS AND PIPING
(2022)
Article
Engineering, Marine
Zhongyan Liu, Jiangtao Mei, Deguo Wang, Yanbao Guo, Lei Wu
Summary: The safety evaluation of steel catenary risers (SCRs), a new type of riser connecting offshore platforms and submarine pipelines, is of great significance due to the long-term exposure to waves and currents. This study proposes a damage identification method for SCRs using acceleration time series signals at multiple locations. A convolutional neural network (CNN) is used to obtain spatial information, while a gated recurrent unit (GRU) neural network is employed to study the variable period characteristics. By combining a CNN with a GRU, a CNN-GRU model is established and optimized using particle swarm optimization (PSO) to form the PSO-CNN-GRU (PCG) model. Experimental results show that the proposed PCG model outperforms existing models (CNN, GRU, and CNN-GRU) in SCR damage identification.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Lei Wu, Xiaodong Huang, Junguo Cui, Chao Liu, Wensheng Xiao
Summary: Path planning is a crucial issue in autonomous navigation of mobile robots. The traditional ant colony optimization algorithm has limitations in terms of convergence speed, efficiency, and local optima. Therefore, a modified adaptive ant colony optimization algorithm (MAACO) is proposed, which introduces new heuristic mechanisms and improves the state transition probability rule to enhance the algorithm's convergence speed and search efficiency, achieving significant improvements in path length, number of turns, and convergence speed.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Hao Yang, Min Wang, Zhengfei Yu, Hang Zhang, Jinshen Jiang, Yun Zhou
Summary: In this paper, a novel method called CSTTA is proposed for test time adaptation (TTA), which utilizes confidence-based optimization and sample reweighting to better utilize sample information. Extensive experiments demonstrate the effectiveness of the proposed method.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Jin Liu, Ju-Sheng Mi, Dong-Yun Niu
Summary: This article focuses on a novel method for generating a canonical basis for decision implications based on object-induced operators (OE operators). The logic of decision implication based on OE operators is described, and a method for obtaining the canonical basis for decision implications is given. The completeness, nonredundancy, and optimality of the canonical basis are proven. Additionally, a method for generating true premises based on OE operators is proposed.
KNOWLEDGE-BASED SYSTEMS
(2024)
Review
Computer Science, Artificial Intelligence
Kun Bu, Yuanchao Liu, Xiaolong Ju
Summary: This paper discusses the importance of sentiment analysis and pre-trained models in natural language processing, and explores the application of prompt learning. The research shows that prompt learning is more suitable for sentiment analysis tasks and can achieve good performance.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Xiangjun Cai, Dagang Li
Summary: This paper presents a new decomposition mechanism based on learned decomposition mapping. By using a neural network to learn the relationship between original time series and decomposed results, the repetitive computation overhead during rolling decomposition is relieved. Additionally, extended mapping and partial decomposition methods are proposed to alleviate boundary effects on prediction performance. Comparative studies demonstrate that the proposed method outperforms existing RDEMs in terms of operation speed and prediction accuracy.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Xu Wu, Yang Liu, Jie Tian, Yuanpeng Li
Summary: This paper proposes a blockchain-based privacy-preserving trust management architecture, which adopts federated learning to train task-specific trust models and utilizes differential privacy to protect device privacy. In addition, a game theory-based incentive mechanism and a parallel consensus protocol are proposed to improve the accuracy of trust computing and the efficiency of consensus.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Zaiyang Yu, Prayag Tiwari, Luyang Hou, Lusi Li, Weijun Li, Limin Jiang, Xin Ning
Summary: This study introduces a 3D view-based approach that effectively handles occlusions and leverages the geometric information of 3D objects. The proposed method achieves state-of-the-art results on occluded ReID tasks and exhibits competitive performance on holistic ReID tasks.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Yongliang Shi, Runyi Yang, Zirui Wu, Pengfei Li, Caiyun Liu, Hao Zhao, Guyue Zhou
Summary: Neural implicit representations have gained attention due to their expressive, continuous, and compact properties. However, there is still a lack of research on city-scale continual implicit dense mapping based on sparse LiDAR input. In this study, a city-scale continual neural mapping system with a panoptic representation is developed, incorporating environment-level and instance-level modeling. A tailored three-layer sampling strategy and category-specific prior are proposed to address the challenges of representing geometric information in city-scale space and achieving high fidelity mapping of instances under incomplete observation.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Ruihan Hu, Zhi-Ri Tang, Rui Yang, Zhongjie Wang
Summary: Mesh data is crucial for 3D computer vision applications worldwide, but traditional deep learning frameworks have struggled with handling meshes. This paper proposes MDSSN, a simple mesh computation framework that models triangle meshes and represents their shape using face-based and edge-based Riemannian graphs. The framework incorporates end-to-end operators inspired by traditional deep learning frameworks, and includes dedicated modules for addressing challenges in mesh classification and segmentation tasks. Experimental results demonstrate that MDSSN outperforms other state-of-the-art approaches.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Buliao Huang, Yunhui Zhu, Muhammad Usman, Huanhuan Chen
Summary: This paper proposes a novel semi-supervised conditional normalizing flow (SSCFlow) algorithm that combines unsupervised imputation and supervised classification. By estimating the conditional distribution of incomplete instances, SSCFlow facilitates imputation and classification simultaneously, addressing the issue of separated tasks ignoring data distribution and label information in traditional methods.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Deeksha Varshney, Asif Ekbal, Erik Cambria
Summary: This paper focuses on the neural-based interactive dialogue system that aims to engage and retain humans in long-lasting conversations. It proposes a new neural generative model that combines step-wise co-attention, self-attention-based transformer network, and an emotion classifier to control emotion and knowledge transfer during response generation. The results from quantitative, qualitative, and human evaluation show that the proposed models can generate natural and coherent sentences, capturing essential facts with significant improvement over emotional content.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Junchen Ye, Weimiao Li, Zhixin Zhang, Tongyu Zhu, Leilei Sun, Bowen Du
Summary: Modeling multivariate time series has long been a topic of interest for scholars in various fields. This paper introduces MvTS, an open library based on Pytorch, which provides a unified framework for implementing and evaluating these models. Extensive experiments on public datasets demonstrate the effectiveness and universality of the models reproduced by MvTS.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Reham R. Mostafa, Ahmed M. Khedr, Zaher Al Aghbari, Imad Afyouni, Ibrahim Kamel, Naveed Ahmed
Summary: Feature selection is crucial in classification procedures, but it faces challenges in high-dimensional datasets. To overcome these challenges, this study proposes an Adaptive Hybrid-Mutated Differential Evolution method that incorporates the mechanics of the Spider Wasp Optimization algorithm and the concept of Enhanced Solution Quality. Experimental results demonstrate the effectiveness of the method in terms of accuracy and convergence speed, and it outperforms contemporary cutting-edge algorithms.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Ti Xiang, Pin Lv, Liguo Sun, Yipu Yang, Jiuwu Hao
Summary: This paper introduces a Track Classification Model (TCM) based on marine radar, which can effectively recognize and classify shipping tracks. By using a feature extraction network with multi-feature fusion and a dataset production method to address missing labels, the classification accuracy is improved, resulting in successful engineering application in real scenarios.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Zhihao Zhang, Yuan Zuo, Chenghua Lin, Junjie Wu
Summary: This paper proposes a novel unsupervised context-aware quality phrase mining framework called LMPhrase, which is built upon large pre-trained language models. The framework mines quality phrases as silver labels using a parameter-free probing technique on the pre-trained language model BERT, and formalizes the phrase tagging task as a sequence generation problem by fine-tuning on the Sequence to-Sequence pre-trained language model BART. The results of extensive experiments show that LMPhrase consistently outperforms existing competitors in two different granularity phrase mining tasks.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Kemal Buyukkaya, M. Ozan Karsavuran, Cevdet Aykanat
Summary: The study aims to investigate the hybrid parallelization of the Stochastic Gradient Descent (SGD) algorithm for solving the matrix completion problem on a high-performance computing platform. A hybrid parallel decentralized SGD framework with asynchronous inter-process communication and a novel flexible partitioning scheme is proposed to achieve scalability up to hundreds of processors. Experimental results on real-world benchmark datasets show that the proposed algorithm achieves 6x higher throughput on sparse datasets compared to the state-of-the-art, while achieving comparable throughput on relatively dense datasets.
KNOWLEDGE-BASED SYSTEMS
(2024)